ClawAudit verdict
exa-research
exa-research-openclaw-skill
The skill uses the local Exa CLI for web search and information retrieval, and it accesses API keys, which could be risky.
โ Flagged for review โ coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
Automated static analysis โ not a human review. ClawAudit flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
Findings (2)
Possible hardcoded credential
scripts/exa-with-key.sh ยท prose ยท downgraded ยท API_KEY="$(head -n 1
Sets world-executable permissions
README.md ยท code ยท chmod 700
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class B). Final tier capped at Caution โ cannot be lifted by any downgrade, example-payload opt-in, or allowlist.
Permissions & capabilities
No declared permissions โ minimal attack surface.
Is this flag fair?
Thanks โ recorded.