Caveat verdict
glm-search-pro
Web search skill using Zhipu GLM API; MCP mode stores API key in a local config file with 600 permissions due to broker SSE limitations, which is transparently documented and owner-controlled.
⚠ 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.
Permission integrity
network_out
Findings (3)
Possible hardcoded credential
SKILL.md · code · API_KEY="your-api-key
Python os.environ.get — reads environment variable
scripts/glm-search.sh · prose · downgraded · os.environ.get(
Sets world-executable permissions
scripts/setup.sh · prose · downgraded · chmod 700
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class B). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.
Permissions & capabilities
No declared permissions — minimal attack surface.
network_outcredential_accessnetwork_in Is this flag fair?
Thanks — recorded.