ClawAudit verdict
glm-image
The skill requires a GLM_API_KEY or OPENROUTER_API_KEY to function, which is used to generate images from text prompts. The usage is transparent and matches the stated purpose.
โ 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. ClawAudit flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
Permission integrity
credential_access
Findings (1)
Python os.environ.get โ reads environment variable
scripts/generate.py ยท prose ยท downgraded ยท os.environ.get(
Permissions & capabilities
No declared permissions โ minimal attack surface.
credential_access Is this flag fair?
Thanks โ recorded.