Caveat verdict

agent-profile-images

88
🟢 Trusted
No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.

Adds profile image management to OpenClaw Control UI without executing untrusted code.

⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.

Automated static analysis — not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.

60
security
100
transparency
90
maintenance

Findings (7)

Pattern match medium

Dynamic import() — loads module at runtime

references/src-gateway-protocol-index-ts.txt · prose · downgraded · import("

Pattern match medium

Instructs covert action — may act without user awareness

references/src-gateway-protocol-schema-agent-ts.txt · prose · downgraded · silently

Pattern match medium

Uses exec() — may execute shell commands

references/src-gateway-server-methods-agents-ts.txt · prose · downgraded · exec(

Pattern match low

References agent configuration files

references/src-gateway-server-methods-agents-ts.txt · prose · downgraded · AgentConfig

Pattern match low

Accesses sensitive environment variables

references/src-gateway-server-methods-agents-ts.txt · prose · downgraded · process.env.ANTHROPIC_API_KEY

Pattern match low

Opens WebSocket connection

references/src-gateway-server-methods-list-ts.txt · prose · downgraded · WebSocket

Pattern match low

References webhook/callback URL

references/ui-src-ui-types-ts.txt · prose · downgraded · webhookUrl

Permissions & capabilities

No declared permissions — minimal attack surface.

Is this flag fair?

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