Caveat verdict

aura-openclaw

88
๐ŸŸข Trusted
No high-risk patterns surfaced by the deep scan โ€” automated capability review, not behavioral proof.

Persistent memory skill that compiles local documents into queryable archives and stores facts across sessions; credential_access is limited to env vars listed as empty in the metadata, and all operations are local with no evidence of data exfiltration.

โš  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. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.

68
security
20
transparency
70
maintenance

Permission integrity

Code accesses API keys/tokens but declares no environment variables

credential_access

Installs packages at runtime โ€” transitive dependencies are not auditable

package_install

Findings (2)

Pattern match medium

Instructs covert action โ€” may act without user awareness

README.md ยท prose ยท downgraded ยท silently

Pattern match low

References agent memory files

README.md ยท prose ยท downgraded ยท MEMORY.md

Permissions & capabilities

No declared permissions โ€” minimal attack surface.

package_installcredential_access

Is this flag fair?

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