Skills/PyPI/sabel-forge-mcp

sabel-forge-mcp@0.4.11

VERIFIED· not started

Publisher claims: "MCP server suite for Intercom workspace and Fin AI configuration, audit, and migration." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher forge · publishing for 192 daysInstalls 2,665Last detonated 31 min ago
$claude mcp add sabel-forge-mcp -- uvx sabel-forge-mcp
WatchReport an issue

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: Verified 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 intercom.io, forge.dev, fly.dev — 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 -- uvx sabel-forge-mcp

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

What changed since 0.4.7

vet-skills diff sabel-forge-mcp 0.4.7 0.4.11

In the sandbox, this version reached for nothing 0.4.7 did not. Compared from the two recorded runs, not from source.

0.4.7 was not run in the sandbox (install failed); the comparison covers what static analysis recorded only.

The guard can hold an update like this until someone approves it (runtime.on_change: hold). A change that only shows with a real credential, or on a path the run did not reach, is not in a trace and so not in this comparison.

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 2026-11-16 and scored it 82/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. 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
0.1sprocessdependency install exit 1 ·
0.1sclaimednot started: dependency install failed (exit 1); the server itself was not observed
0.1sprocessscript backend runs setup only
0.1sprocessno install scripts to re-run

Static findings

MEDIUM
Python subprocess execution detectedforge/mcp/fin/tools/procedures.py:38 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File permission modification commandforge/mcp/workspaces_tool.py:236 · File permission modification command — agent changes file ownership/permissions# 5. Normalise industry + deployment, write the config (atomic, chmod 600).Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Python subprocess execution detectedforge/commands/update.py:86 · Python subprocess execution detectedresult = subprocess.run(cmd, encoding="utf-8", errors="replace")Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedforge/mcp/fin/tools/fin_snapshot.py:34 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedforge/mcp/shared_ui.py:102 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File permission modification commandforge/commands/workspace.py:67 · File permission modification command — agent changes file ownership/permissions"""Atomic write — temp file, chmod 600, replace."""Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
HIGH
Hidden zero-width characters detectedforge/ui_automation/macros.py:343 · Hidden zero-width characters detected — may conceal contenttxt = (await ed.inner_text()).strip().replace("​", "")Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST07
MEDIUM
Process kill commandforge/mcp/workspace/tools/audit.py:155 · Process kill command — agent can terminate processesexcept Exception as e: # noqa: BLE001 — one bad read must not kill the auditFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedforge/ui_automation/session.py:293 · Python subprocess execution detectedsubprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
LOW
Unpinned dependencyforge/mcp/fin/tools/fin_attributes.py:83 · Unpinned dependencyit): `npm install -g @intercom/cli@latest` if it's missing.Fix: Pin the exact version (`[email protected]`, `==1.2.3`) so every install gets the bytes that were reviewed.
AST06
MEDIUM
Python subprocess execution detectedforge/ui_automation/cdp_serve.py:171 · Python subprocess execution detectedproc = subprocess.Popen(args)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File permission modification commandforge/org_context.py:14 · File permission modification command — agent changes file ownership/permissionskey never leaves ~/.forge/org_device_key (chmod 600), the public keyFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
File permission modification commandforge/workspace_config.py:74 · File permission modification command — agent changes file ownership/permissionsBest-effort and atomic (tmp + chmod 600 + replace, mirroringFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05

Cost to the agent

Instructions loaded
≈60 tok
1 file · 81 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

Not checked against OSV yet; the weekly check has not reached this version.

sabel-forge-mcp@0.4.11 safety verdict: Verified (not started) — KillerSkills