Caveat verdict

vet-repo

🟢 Trusted

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

Security scanner for agent config files that detects malicious patterns in SKILL.md, .mcp.json, and CLAUDE.md files; advisory-only hooks that warn but don't block.

⚠ 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.

security

transparency

maintenance

Findings (18)

Pattern match high

Pipe to bash — executes piped content as shell commands

SKILL.md · prose · downgraded · |bash

Pattern match high

Recursive delete from root or home — destructive command

SKILL.md · prose · downgraded · rm -rf /

Pattern match high

Pipe to sh — executes piped content as shell commands

scripts/patterns.py · prose · downgraded · |sh

Pattern match high

Pipe to python — executes piped content as Python code

scripts/patterns.py · prose · downgraded · |python

Pattern match high

Uses eval() — can execute arbitrary code

scripts/patterns.py · prose · downgraded · eval(

Pattern match high

Bash /dev/tcp — raw TCP connection via shell

scripts/patterns.py · prose · downgraded · /dev/tcp/

Pattern match high

Accesses sensitive system files

scripts/patterns.py · prose · downgraded · /etc/shadow

Pattern match high

Dynamic Function constructor — equivalent to eval()

scripts/patterns.py · prose · downgraded · new Function(

Pattern match medium

Accesses .ssh directory

SKILL.md · prose · downgraded · .ssh/

Pattern match medium

Uses exec() — may execute shell commands

scripts/patterns.py · prose · downgraded · exec(

Pattern match medium

References child_process — can spawn system processes

scripts/patterns.py · prose · downgraded · child_process

Pattern match medium

Uses spawn() — can execute external programs

scripts/patterns.py · prose · downgraded · spawn(

Pattern match medium

Base64 decode (atob) — may hide malicious payloads

scripts/patterns.py · prose · downgraded · atob(

Pattern match medium

References sudo — requests elevated privileges

scripts/patterns.py · prose · downgraded · sudo

Pattern match low

References agent configuration files

SKILL.md · prose · downgraded · CLAUDE.md

Pattern match low

Sets world-executable permissions

SKILL.md · prose · downgraded · chmod 777

Pattern match low

Base64 encoding/decoding

scripts/patterns.py · prose · downgraded · base64_encode

Pattern match low

Python urllib.request — network access

scripts/patterns.py · prose · downgraded · urllib.request

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class A/D/E). 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?

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