Skills/Glama/rad-mcp

rad-mcp@0.1.0

CAUTION· not started

Publisher claims: "Enables AI assistants to run local Radiance lighting and daylighting simulations on user-owned models, including annual daylight, compliance metrics, renders, glare analysis and electric lighting studies, with reproducible exported scripts." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry GlamaPublisher akontadakis · publishing for 1 daysInstalls 0Last detonated 18 h ago
What would fix thisWatchDispute verdict

Coverage

Not started: dependency install failed; the server itself was not observed.
Tested
the dependency install step · every file read, file written and host contacted by what ran
Not tested
server startup · the tool list · tool behavior

What this means for the label: Caution here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.

Before you give it your token

It will ask for
no credential variables read in the code
Where it talks to
no vendor host named in the codeAlso lbl.gov — not the publisher's domain; check what for before connecting.
What the honeypot saw
no credential files read · no network
What we could not test
server startup · the tool list · tool behavior

Connect it under the guard. Not started: dependency install failed; the server itself was not observed. The code names no credential variable; the guard pins the network to what the honeypot saw and logs every call.

$vet-skills run --net declared -- <the server's command>

Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; not started: dependency install failed; the server itself was not observed) on 2026-11-13 and scored it 75/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Access to sensitive file paths; Access to sensitive file paths; Access to sensitive file paths. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.2sprocessdependency install exit 1 ·
0.2sclaimednot started: dependency install failed (exit 1); the server itself was not observed
0.2sprocessscript backend runs setup only
0.2sprocessno install scripts to re-run

Static findings

HIGH
Access to sensitive file pathssrc/rad_engine/glarendx.py:52 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesfrom .env import RadianceEnvFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathssrc/rad_engine/__init__.py:27 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesfrom .env import RadianceEnv, RadianceNotFound, discoverFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathssrc/rad_engine/image.py:94 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesfrom .env import RadianceEnvFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathssrc/rad_engine/ies.py:31 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesfrom .env import RadianceEnvFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathssrc/rad_engine/jobs.py:75 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesfrom .env import RadianceEnv, raypath_dirs_ofFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathssrc/rad_engine/annual.py:99 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesfrom .env import RadianceEnvFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Hidden zero-width characters detectedsrc/rad_core/weather.py:419 · Hidden zero-width characters detected — may conceal contentreturn text[1:] if text and text[0] == "" else textFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST07
MEDIUM
Process kill commandsrc/rad_engine/jobs.py:1699 · Process kill command — agent can terminate processesand `cancel` whenever they hold the step's process, `_execute`'s post-spawn kill and itsFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Access to sensitive file pathssrc/rad_engine/scene.py:108 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesfrom .env import RadianceEnvFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Python subprocess execution detectedsrc/rad_engine/run.py:9 · Python subprocess execution detected**And stdin is declared on every spawn, including the ones that take none.** `subprocess.run(...,Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Process kill commandsrc/rad_engine/octree.py:719 · Process kill command — agent can terminate processesthe `anyio` worker parked there and the process needed `kill -9`. The `anyio` limiter is 40, soFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedsrc/rad_engine/env.py:320 · Python subprocess execution detectedproc = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Process kill commandsrc/rad_engine/jobs.py:1697 · Process kill command — agent can terminate processes"""Jobs whose step's process group was sent a kill (R775), so an end reason can say whetherFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File type combined with upload actionsrc/rad_mcp/export_tool.py:385 · File type combined with upload action — agent may exfiltrate local data files`"manifest"` writes `manifest.json` (the project record and its registered inputs, or onlyFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Python subprocess execution detectedsrc/rad_engine/jobs.py:1481 · Python subprocess execution detectedprobe = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Process kill commandsrc/rad_engine/run.py:207 · Process kill command — agent can terminate processes# would fall in its kill window after a normal exit (design P10). "" and not None: NoneFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedsrc/rad_engine/run.py:205 · Python subprocess execution detected# Text in and out, as `subprocess.run(text=True)` did, but decoded *after* the helperFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/rad_engine/jobs.py:1598 · Python subprocess execution detectedsubprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Access to sensitive file pathssrc/rad_mcp/annual_tool.py:1298 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files# prefix absorbs the leading segment of a traversal, so `../../etc/passwd` becomesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathssrc/rad_engine/rtrace.py:69 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesfrom .env import RadianceEnvFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Process kill commandsrc/rad_engine/jobs.py:1154 · Process kill command — agent can terminate processesmakes a group kill possible and also means a hard-killed server leaves a live `rcontrib` holdingFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File type combined with upload actionsrc/rad_engine/octree.py:716 · File type combined with upload action — agent may exfiltrate local data fileson 2026-08-09: hand-editing `manifest.json` so a registered geometry input points at a FIFO --Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Python subprocess execution detectedsrc/rad_mcp/glare_tool.py:1690 · Python subprocess execution detected# have passed any of those straight to the first `subprocess.run(..., timeout=...)` spawn --Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Access to sensitive file pathssrc/rad_engine/octree.py:38 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesfrom .env import RadianceEnvFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathssrc/rad_engine/run.py:57 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesfrom .env import RadianceEnvFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File permission modification commandsrc/rad_engine/safe_io.py:380 · File permission modification command — agent changes file ownership/permissionsa `chmod +x`'d `export.sh` keeps its execute bits. Owner and group are not carried: the stageFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
File type combined with upload actionsrc/rad_mcp/export_tool.py:1112 · File type combined with upload action — agent may exfiltrate local data filesand `report.md`, an artifact's copy, `manifest.json` and each input's copy. `export` registersFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
HIGH
Access to sensitive file pathssrc/rad_mcp/annual_tool.py:1299 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files# `dsmx_../../etc/passwd` -- one directory shallower than intended and, on this repo's layout,Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File type combined with upload actionsrc/rad_mcp/export_tool.py:1278 · File type combined with upload action — agent may exfiltrate local data files# `manifest.json`, a restored backup) -- computed from project state, not an argumentFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File permission modification commandsrc/rad_engine/project.py:2439 · File permission modification command — agent changes file ownership/permissions# `chmod 000` is unreadable, so this function cannot prove its bytes are the bound ones,Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Process kill commandsrc/rad_engine/jobs.py:1583 · Process kill command — agent can terminate processes`CTRL_BREAK_EVENT` reaches console children only, so the tree kill goes through `taskkill /T /F`Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandsrc/rad_engine/chain.py:3956 · Process kill command — agent can terminate processes#: tight multiple would kill correct work on a slow host, which is the failure `Step.timeout_s`Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Access to sensitive file pathssrc/rad_engine/render.py:108 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesfrom .env import RadianceEnvFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathssrc/rad_engine/sky.py:138 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesfrom .env import RadianceEnvFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Process kill commandsrc/rad_engine/run.py:35 · Process kill command — agent can terminate processes`kill -9`. The worker pool's limiter is 40, so forty such paths stall every tool the server offers.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedsrc/rad_core/ugr.py:210 · Python subprocess execution detected# to `rad_engine.process_group.run_in_own_session` (R750; `subprocess.run(input=...,Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Process kill commandsrc/rad_engine/scene.py:939 · Process kill command — agent can terminate processes# manifest-registered geometry path pointed at one, the process needed `kill -9`.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Access to sensitive file pathssrc/rad_engine/suns.py:114 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesfrom .env import RadianceEnvFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File permission modification commandsrc/rad_engine/project.py:2413 · File permission modification command — agent changes file ownership/permissionsA file this function **cannot read at all** -- gone, replaced by a directory, `chmod 000`, aFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Process kill commandsrc/rad_engine/jobs.py:1702 · Process kill command — agent can terminate processesleader has exited (R757), so a step whose process is held is sent a kill either way. A jobFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File type combined with upload actionsrc/rad_mcp/export_tool.py:958 · File type combined with upload action — agent may exfiltrate local data files"""`manifest.json` plus a copy of every registered input file it references -- the "ingredients"Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Python subprocess execution detectedsrc/rad_engine/run.py:125 · Python subprocess execution detected"""The encoding `subprocess.Popen(text=True)` chooses for its pipes in this process: aFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Access to sensitive file pathssrc/rad_engine/klems.py:96 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesfrom .env import RadianceEnvFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Process kill commandsrc/rad_mcp/server.py:2121 · Process kill command — agent can terminate processes# R750: inline Radiance children run in their own session, so the client's group kill noFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedsrc/rad_engine/glarendx.py:314 · Python subprocess execution detected`subprocess.run(input=..., capture_output=True)` before it), whose `Popen.communicate` buffersFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/rad_engine/jobs.py:1431 · Python subprocess execution detectedreturn subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Access to sensitive file pathssrc/rad_engine/rpict.py:117 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesfrom .env import RadianceEnvFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File type combined with upload actionsrc/rad_mcp/export_tool.py:248 · File type combined with upload action — agent may exfiltrate local data filesmanifest.json listed BOTH inputs; advisories: NoneFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Python subprocess execution detectedsrc/rad_mcp/timeouts.py:46 · Python subprocess execution detected`subprocess.run(..., timeout=1e9)` spawn *during* `dry_run=True` and raises an uncaughtFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/rad_mcp/timeouts.py:79 · Python subprocess execution detected`subprocess.run(..., timeout=...)` spawn, but as different exception types (the boundary tableFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/rad_mcp/timeouts.py:4 · Python subprocess execution detectedby driving `subprocess.run([sys.executable, "-c", "import time; time.sleep(0.2)"], timeout=t,Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/rad_mcp/timeouts.py:7 · Python subprocess execution detected`subprocess.run(..., timeout=t)` with **no** piped stream does *not* reproduce this on thisFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05

Cost to the agent

Instructions loaded
≈7,739 tok
2 files · 80 in bundle
Tool list per prompt
≈0 tok
0 tools · 0 per tool
Handshake
no reply
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 0

Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.

Known vulnerabilities

Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.

What would make this Verified

5 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim akontadakis: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  3. Hidden zero-width characters detected≈ +4 on the totalKeep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
  4. Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  5. Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
  6. File type combined with upload action≈ +2 on the totalRemove the call, or declare the host in frontmatter and explain in the README what is sent and why.
Publish a new version to Glama, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim akontadakisPropose a patch to the maintainer