Caveat verdict

crewai-team

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

A CrewAI multi-agent skill for product requirement analysis and PRD generation that uses process_exec only to run user-configured Python scripts with a DashScope API key; the behavior matches its stated purpose.

⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.

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
80
transparency
70
maintenance

Findings (8)

Pattern match critical

Possible hardcoded credential

COMPLETE.md · code · API_KEY="sk-your-actual-key-here

Pattern match critical

Pipe-to-shell pattern (curl | sh) — supply chain attack vector

USAGE.md · code · curl -LsSf https://astral.sh/uv/install.sh | sh

Pattern match critical

Pipe to sh — executes piped content as shell commands

USAGE.md · code · | sh

Pattern match high

Pipe to python — executes piped content as Python code

COMPLETE.md · prose · downgraded · | Python

Pattern match high

Accesses shell history/config

SETUP.md · code · ~/.zshrc

Pattern match medium

Opens WebSocket connection

PARALLEL_DISCUSSION.md · code · WebSocket

Pattern match medium

Python os.environ.get — reads environment variable

USAGE.md · code · os.environ.get(

Pattern match low

Popular HTTP library — network access

prd_sequential_20260310_154832.md · prose · downgraded · axios

Why the tier is capped

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

Permissions & capabilities

Requires 1 system binary.

process_exec

Is this flag fair?

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