ClawAudit verdict
weryai-image-generator
Image generation skill via the WeryAI API using user-supplied credentials; all network calls go to the declared WeryAI endpoints for the stated image generation purpose.
⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
Automated static analysis — not a human review. ClawAudit flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
Findings (5)
Possible hardcoded credential
SKILL.md · code · API_KEY="your_api_key_here
References child_process — can spawn system processes
scripts/vendor/weryai-image/main.ts · prose · downgraded · child_process
Accesses sensitive environment variables
scripts/lib/cli.js · prose · downgraded · process.env.WERYAI_API_KEY
References webhook/callback URL
scripts/vendor/shared-image-generation/scripts/main.ts · prose · downgraded · webhookUrl
Popular HTTP library — network access
scripts/vendor/weryai-image/model-registry.js · prose · downgraded · got
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class D). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.
Permissions & capabilities
Requires 3 environment variables. (1 sensitive: WERYAI_API_KEY). Requires 1 system binary.
Is this flag fair?
Thanks — recorded.