ClawAudit verdict
paperbanana
openclaw-paperbanana
Academic diagram generation skill using a multi-agent pipeline via GOOGLE_API_KEY; all operations match the stated purpose of generating publication-quality figures from text descriptions.
⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
Automated static analysis — not a human review. ClawAudit flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
Findings (5)
Possible hardcoded credential
SKILL.md · code · API_KEY: "sk-or-...
Pipe-to-shell pattern (curl | sh) — supply chain attack vector
README.md · code · curl -LsSf https://astral.sh/uv/install.sh | sh
Pipe to sh — executes piped content as shell commands
README.md · code · | sh
Accesses OpenClaw config/secrets directly
references/providers.md · code · ~/.openclaw/openclaw.json
Python os.environ.get — reads environment variable
scripts/evaluate.py · prose · downgraded · os.environ.get(
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class A/B). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.
Permissions & capabilities
Requires 1 system binary.
data_encoding Is this flag fair?
Thanks — recorded.