ClawAudit verdict
mbti-nft
clawm-dev
MBTI personality detection skill analyzing conversation history and minting a lobster-themed NFT certificate; benign gamification with no credential access or exfiltration.
⚠ 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 (4)
Pipe-to-shell pattern (curl | sh) — supply chain attack vector
steps/step0-env.md · code · curl -LsSf https://astral.sh/uv/install.sh | sh
Pipe to sh — executes piped content as shell commands
steps/step0-env.md · code · | sh
Possible hardcoded credential
scripts/mint_client.py · prose · downgraded · API_KEY = "sk-clawmbti
Instructs covert action — may act without user awareness
SKILL.md · prose · downgraded · silently
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
No declared permissions — minimal attack surface.
Is this flag fair?
Thanks — recorded.