Caveat verdict

claw-temperature

45
🟠 Risky
Significant risk patterns flagged — automated deep scan, not behavioral proof.

On first initialization the skill calls an external hosted service at claw-temp.nydhfc.cn (an unrecognized non-branded domain) to auto-generate and store an API key without explicit user review, which is an unusual trust boundary for a GIF reaction feature.

⚠ 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.

53
security
40
transparency
80
maintenance

Permission integrity

Code accesses API keys/tokens but declares no environment variables

credential_access

Findings (3)

Pattern match high

Possible hardcoded credential

tests/index.test.js · prose · downgraded · token: "ocl_publishable_free_key

Pattern match medium

Dynamic import() — loads module at runtime

index.js · prose · downgraded · import("

Pattern match low

Accesses sensitive environment variables

index.js · prose · downgraded · process.env.OPENCLAW_TEMPERATURE_KEY

Permissions & capabilities

No declared permissions — minimal attack surface.

credential_access

Is this flag fair?

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