Caveat verdict

skill-integrity-auditor

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

Mandatory security auditor inspecting skill bundles for prompt injection, exfiltration, and hardcoded credentials; reads skill files locally with no network output.

⚠ 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
70
transparency
90
maintenance

Permission integrity

Performs file operations but does not declare file-accessing binaries

file_read

Findings (11)

Pattern match critical

Unicode homoglyph detected — uses lookalike characters to evade pattern matching

SKILL.md · prose

Pattern match high

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

SKILL.md · prose · downgraded · curl \| sh

Pattern match high

Pipe to sh — executes piped content as shell commands

SKILL.md · prose · downgraded · | sh

Pattern match high

Writes to SKILL.md — self-modifying skill

SKILL.md · prose · downgraded · SKILL.md** that instructs the agent to read a specific user / workspace / enviro

Pattern match medium

Instructs covert action — may act without user awareness

SKILL.md · prose · downgraded · silently

Pattern match medium

Accesses system credential store

SKILL.md · prose · downgraded · Keychain

Pattern match medium

Accesses cloud provider credentials

SKILL.md · prose · downgraded · ~/.aws

Pattern match low

Sets world-executable permissions

SKILL.md · prose · downgraded · chmod 777

Pattern match low

Opens WebSocket connection

SKILL.md · prose · downgraded · Websocket

Pattern match low

Base64 encoding/decoding

SKILL.md · prose · downgraded · base64-encode

Pattern match low

References tunneling service

SKILL.md · prose · downgraded · ngrok

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class A). 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_read

Is this flag fair?

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