Caveat verdict
lark-toolkit
Accesses credentials AND makes external network calls
A documentation-only reference for the Lark/Feishu API using user-supplied app credentials; the skill explicitly states no credentials are hardcoded or cached, and all API calls go to documented Lark endpoints.
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.
What it does
These are capability combinations: each listed behavior occurs in the skill, but Caveat detects co-occurrence — it does not verify that one flows into another. Read the code to confirm a live chain.
Accesses credentials AND makes external network calls — potential credential theft
LLM02 · ASI03
Permission integrity
network_out
credential_access
Findings (6)
Pipe to python — executes piped content as Python code
SKILL.md · code · | python3
HTTP request to bare IP address — common in malicious payloads
references/webhook-setup.md · code · http://127.0.0.1
Possible hardcoded credential
scripts/get_token.sh · prose · downgraded · SECRET="${2:-${LARK_APP_SECRET:-}}
Accesses OpenClaw config/secrets directly
references/bot-setup.md · prose · downgraded · ~/.openclaw/openclaw.json
References tunneling service
references/bot-setup.md · code · ngrok
Opens WebSocket connection
references/webhook-setup.md · prose · downgraded · websocket
Permissions & capabilities
No declared permissions — minimal attack surface.
network_outcredential_access Thanks — recorded.