Caveat verdict

openclawarena-arena

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

Game arena API for registering and managing AI agents in a game platform; all calls go to the documented arena API with user-provided credentials.

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.

45
security
40
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 high

Possible hardcoded credential

scripts/openclawarena.sh ยท prose ยท downgraded ยท API_KEY="${OCA_API_KEY:-735BLLoQuk9NuDT3Z2nqO4IqGYBWcpmH96OGgzv9}

Pattern match medium

Opens WebSocket connection

SKILL.md ยท code ยท WebSocket

Permissions & capabilities

Requires 2 system binaries. (1 elevated: curl).

package_installnetwork_incredential_access

Is this flag fair?

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