Caveat verdict
smart-search
Accesses credentials AND makes external network calls
Multi-engine web search tool using Exa MCP, SearX, and Tavily APIs — reads API key from environment for its legitimate core function, all external endpoints are named official platforms, no exfiltration.
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 (9)
Possible hardcoded credential
README.searx.md · code · SECRET='local-secret-2026
Recursive delete from root or home — destructive command
README.searx.md · code · rm -rf ~
Uses eval() — can execute arbitrary code
VETTING.md · code · eval(
Accesses OpenClaw config/secrets directly
SKILL.md · code · ~/.openclaw/.env
References sudo — requests elevated privileges
README.searx.md · code · sudo
Uses exec() — may execute shell commands
VETTING.md · code · exec(
Accesses cloud provider credentials
VETTING.md · code · ~/.aws
Sets world-executable permissions
SECURITY_AUDIT.md · code · chmod 777
References agent memory files
VETTING.md · code · MEMORY.md
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.
credential_accessnetwork_out Thanks — recorded.