ClawAudit verdict
gr-seo-patrol
Reads local files AND makes external network calls
Uses DATAFORSEO_B64 to query a legitimate SERP API and GITHUB_TOKEN to read/write _posts/ blog files; all credential usage is scoped to the skill's stated SEO patrol and canonical-fix purposes with no exfiltration to unexpected destinations.
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.
What it does
These are capability combinations: each listed behavior occurs in the skill, but ClawAudit detects co-occurrence — it does not verify that one flows into another. Read the code to confirm a live chain.
Reads local files AND makes external network calls — the capabilities for data exfiltration co-occur (data-flow not verified)
LLM02 · LLM06 · ASI03
Reads files, encodes data, AND makes external network calls — the obfuscated-exfiltration pattern (data-flow not verified)
LLM02 · ASI03
Accesses credentials AND makes external network calls — potential credential theft
LLM02 · ASI03
Accesses credentials AND encodes data — may obfuscate stolen credentials
LLM02 · ASI03 · ASI04
Permission integrity
network_out
file_read
credential_access
Findings (3)
<script> tag in markdown — potential code injection
gr-seo-patrol/scripts/check-schema.py · prose · downgraded · <script
Python urllib.request — network access
SKILL.md · code · urllib.request
Python os.environ.get — reads environment variable
gr-seo-patrol/scripts/canonical-fix.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.
network_outfile_readcredential_accessdata_encoding Thanks — recorded.