ClawAudit verdict

agentsource

lead-enricher-explorium-agentsource

88
🟢 Trusted
Low risk — reviewed by ClawAudit, behavior matches stated purpose

B2B lead discovery and enrichment skill using the AgentSource database; file_read capability is appropriate for reading existing contact lists, and the skill serves a clear legitimate sales prospecting purpose.

⚠ 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.

38
security
70
transparency
70
maintenance

Permission integrity

Performs file operations but does not declare file-accessing binaries

file_read

Findings (4)

Pattern match critical

Possible hardcoded credential

SKILL.md · frontmatter · credential: "EXPLORIUM_API_KEY (env var or ~/.agentsource/config.json) — your Ex

Pattern match high

Accesses shell history/config

README.md · code · ~/.zshrc

Pattern match low

Python urllib.request — network access

bin/agentsource.py · prose · downgraded · urllib.request

Pattern match low

Python os.environ.get — reads environment variable

bin/agentsource.py · prose · downgraded · os.environ.get(

Why the tier is capped

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

file_read

Is this flag fair?

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