Caveat verdict
feishu-skills-kit
A collection of 10 Feishu integration skills covering documents, messaging, spreadsheets, and workflow automation; agent_memory is used for cross-group message search and digest, consistent with the stated purpose, with no evidence of exfiltration or deceptive behavior.
⚠ 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
agent_memory
Findings (8)
Possible hardcoded credential
README.md · code · SECRET="your_app_secret_here
Opens WebSocket connection
skills/feishu-bridge/SKILL.md · frontmatter · WebSocket
References tunneling service
skills/feishu-bridge/SKILL.md · frontmatter · ngrok
References child_process — can spawn system processes
skills/feishu-card/handle_event.js · prose · downgraded · child_process
Uses spawn() — can execute external programs
skills/feishu-memory-recall/recall.js · prose · downgraded · spawn(
Popular HTTP library — network access
skills/feishu-bitable/add_task_dynamic.js · prose · downgraded · node-fetch
Accesses sensitive environment variables
skills/feishu-memory-recall/index.js · prose · downgraded · process.env.FEISHU_APP_SECRET
Python os.getenv — reads environment variable
skills/feishu-sheets-skill/scripts/feishu_sheets.py · prose · downgraded · os.getenv(
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class B/D). 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.
agent_memory Is this flag fair?
Thanks — recorded.