Caveat verdict

ai-collab

88
🟢 Trusted
No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.

Accesses credentials AND makes external network calls

This skill sets up a two-agent collaboration system using local filesystem-based inbox/chat log coordination and tmux sessions — all operations are transparent local orchestration consistent with its stated multi-agent communication purpose.

Automated static analysis — not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.

0
security
50
transparency
70
maintenance

What it does

These are capability combinations: each listed behavior occurs in the skill, but Caveat detects co-occurrence — it does not verify that one flows into another. Read the code to confirm a live chain.

Capability combination high

Accesses credentials AND makes external network calls — potential credential theft

LLM02 · ASI03

Capability combination high

Accesses credentials AND encodes data — may obfuscate stolen credentials

LLM02 · ASI03 · ASI04

Capability combination high

Accesses credentials AND writes files — may persist stolen credentials locally

LLM02 · LLM06 · ASI03

Permission integrity

Makes network requests but does not declare curl/wget in required binaries

network_out

Performs file operations but does not declare file-accessing binaries

file_read+write

Code accesses API keys/tokens but declares no environment variables

credential_access

Findings (6)

Pattern match critical

Pipe to python — executes piped content as Python code

references/telegram-bridge.md · code · | python3

Pattern match critical

Possible hardcoded credential

references/telegram-bridge.md · code · TOKEN="${TELEGRAM_BOT_TOKEN:?TELEGRAM_BOT_TOKEN not set}

Pattern match high

Accesses OpenClaw config/secrets directly

SKILL.md · code · ~/.openclaw/.env

Pattern match high

Pipe-to-python pattern — remote code execution risk

references/telegram-bridge.md · prose · downgraded · curl -s "https://api.telegram.org/bot<BOT_TOKEN>/getUpdates" | python

Pattern match medium

Python os.environ.get — reads environment variable

examples/claude-gpt.md · code · os.environ.get(

Pattern match low

References agent configuration files

skill-card.md · prose · downgraded · claude.md

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class B). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.

Permissions & capabilities

No declared permissions — minimal attack surface.

file_writedata_encodingnetwork_outcredential_accessnetwork_in
Check another skill Browse the registry Auditing your own skills or configs? Use the API