Skills/Glama/ouroboros

ouroboros@r1

CAUTION· not started

Publisher claims: "Enables AI coding agents to run a specification-first workflow with Socratic interviews, immutable seed specs, staged evaluation gates, and persistent evolutionary loops across multiple runtimes." Observed in sandbox: calls pypi.org only, touches nothing outside the project, writes no memory.

Registry GlamaPublisher acrt-eval · publishing for 0 daysInstalls 0Last detonated 2 h ago
What would fix thisWatchDispute verdict

Coverage

Not started: dependency install failed; the server itself was not observed.
Tested
install scripts, with decoy credentials in place · second launch with the clock 45 days ahead · 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 astral.sh, githubusercontent.com, python.org, claude.ai — not the publisher's domain; check what for before connecting.
What the honeypot saw
no credential files read · reached only pypi.org
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 ouroboros@r1 safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (3 scenarios; not started: dependency install failed; the server itself was not observed) on 2026-11-15 and scored it 62/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Pipe-to-shell pattern; Direct script execution from GitHub raw URL; Collapsed <details> block carrying instructions. Summary: calls pypi.org only, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 1 s · 3 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessinstall script run in the sandbox
0.4snetworkCONNECT tcp://pypi.org:443
0.4sprocessexec /usr/bin/curl
0.4sprocessexec /usr/bin/grep
0.4sprocessexec /usr/bin/sort
0.4sprocessexec /usr/bin/head
0.4sprocessexited 1:
0.5sprocessdependency install exit 1 ·
0.5sclaimednot started: dependency install failed (exit 1); the server itself was not observed
0.6sprocessscript backend runs setup only
0.8sprocesssecond launch, clock +45 days, CI unset
1.1snetworkCONNECT tcp://pypi.org:443
1.1sprocessexec /usr/bin/curl
1.1sprocessexec /usr/bin/grep
1.1sprocessexec /usr/bin/sort
1.1sprocessexec /usr/bin/head
1.1sprocessexited 1:

Static findings

HIGH
Pipe-to-shell patternskills/setup/SKILL.md:155 · Pipe-to-shell pattern — downloads and immediately executes remote codecurl -LsSf https://astral.sh/uv/install.sh | shFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
MEDIUM
Python subprocess execution detectedscripts/ralph-rewind.py:75 · Python subprocess execution detectedsubprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/sync-plugin-version.py:40 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Direct script execution from GitHub raw URLscripts/install.sh:3 · Direct script execution from GitHub raw URL — unverified code source# Usage: curl -fsSL https://raw.githubusercontent.com/Q00/ouroboros/main/scripts/install.sh | bashFix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Collapsed <details> block carrying instructionsREADME.md:84 · Collapsed <details> block carrying instructions<summary><strong>Other install methods</strong></summary> **Claude Code plugin only** (no system package): ```bash claude plugin marketplace add Q00/ouroboros &Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Remote installer piped to shellscripts/install.sh:113 · Remote installer piped to shell# Pipe mode (curl | bash): install base package, skip runtime-specific setupFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
HIGH
Privileged sudo commandskills/setup/SKILL.md:562 · Privileged sudo command — agent may execute with elevated privilegesUbuntu: sudo apt install python3.12Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Collapsed <details> block carrying instructionsREADME.md:131 · Collapsed <details> block carrying instructions<summary><strong>What just happened?</strong></summary> ``` interview -> Socratic questioning exposed 12 hidden assumptions seed -> Crystallized answers into anFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
CRITICAL
Pipe-to-shell patternscripts/install.sh:3 · Pipe-to-shell pattern — downloads and immediately executes remote code# Usage: curl -fsSL https://raw.githubusercontent.com/Q00/ouroboros/main/scripts/install.sh | bashFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
CRITICAL
Pipe-to-shell patternscripts/install.sh:113 · Pipe-to-shell pattern — downloads and immediately executes remote code# Pipe mode (curl | bash): install base package, skip runtime-specific setupFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
MEDIUM
Process kill commandscripts/keyword-detector.py:121 · Process kill command — agent can terminate processes"kill stuck",Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Instructs the agent to modify its persistent memory or instruction filesskills/setup/SKILL.md:231 · Instructs the agent to modify its persistent memory or instruction filesAdd Ouroboros quick-reference to your CLAUDE.md?Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
CRITICAL
Pipe-to-shell patternscripts/install.sh:58 · Pipe-to-shell pattern — downloads and immediately executes remote codeecho " • uv (recommended): curl -LsSf https://astral.sh/uv/install.sh | sh"Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
MEDIUM
Python subprocess execution detectedscripts/sync-plugin-version.py:27 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
CRITICAL
Pipe-to-shell patternsrc/ouroboros/cli/commands/setup.py:95 · Pipe-to-shell pattern — downloads and immediately executes remote code"Install with: curl -LsSf https://astral.sh/uv/install.sh | sh"Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
MEDIUM
Remote installer piped to shellscripts/install.sh:3 · Remote installer piped to shell# Usage: curl -fsSL https://raw.githubusercontent.com/Q00/ouroboros/main/scripts/install.sh | bashFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
HIGH
Pipe-to-shell patternskills/setup/SKILL.md:166 · Pipe-to-shell pattern — downloads and immediately executes remote codecurl -LsSf https://astral.sh/uv/install.sh | shFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
MEDIUM
Remote installer piped to shellscripts/install.sh:58 · Remote installer piped to shellecho " • uv (recommended): curl -LsSf https://astral.sh/uv/install.sh | sh"Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
HIGH
Instructs the agent to modify its persistent memory or instruction filesskills/update/SKILL.md:150 · Instructs the agent to modify its persistent memory or instruction filesd. **Verify and update CLAUDE.md version marker**:Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Remote installer piped to shellsrc/ouroboros/cli/commands/setup.py:95 · Remote installer piped to shell"Install with: curl -LsSf https://astral.sh/uv/install.sh | sh"Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
MEDIUM
Process kill commandskills/cancel/SKILL.md:18 · Process kill command — agent can terminate processes**Trigger keywords:** "cancel execution", "kill session", "stop running", "abort execution"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandskills/help/SKILL.md:78 · Process kill command — agent can terminate processes| "cancel execution", "stop job", "kill stuck", "abort execution" | `ooo cancel` |Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Remote installer piped to shellskills/setup/SKILL.md:166 · Remote installer piped to shellcurl -LsSf https://astral.sh/uv/install.sh | shFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
MEDIUM
Python subprocess execution detectedsrc/ouroboros/cli/commands/setup.py:60 · Python subprocess execution detectedsubprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Remote installer piped to shellskills/setup/SKILL.md:155 · Remote installer piped to shellcurl -LsSf https://astral.sh/uv/install.sh | shFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07

Cost to the agent

Instructions loaded
≈29,602 tok
18 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

18 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim acrt-eval: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Hidden instructions≈ +6 on the totalRemove HTML comments, zero-width characters and white-on-white text that carry instructions. Everything the agent is meant to read should be visible to the person reading the file.
  3. Pipe-to-shell pattern≈ +4 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
  4. Direct script execution from GitHub raw URL≈ +4 on the totalPin versions and sources; vendor anything fetched at install time.
  5. Privileged sudo command≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  6. Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
Publish a new version to Glama, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim acrt-evalPropose a patch to the maintainer