Caveat verdict
openclaw-security-hardening
Defensive security toolkit that scans skill files for prompt injection, exfiltration patterns, hidden unicode, and obfuscated commands with no outbound data transmission; all tools are described in detail for the stated protective purpose.
⚠ 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.
Findings (8)
Pipe to bash — executes piped content as shell commands
scripts/install-guard.sh · prose · downgraded · |bash
Accesses sensitive system files
scripts/install-guard.sh · prose · downgraded · /etc/passwd
Pipe to sh — executes piped content as shell commands
scripts/install-guard.sh · prose · downgraded · |sh
Pipe to python — executes piped content as Python code
scripts/install-guard.sh · prose · downgraded · |python
References agent memory files
SKILL.md · prose · downgraded · MEMORY.md
Popular HTTP library — network access
scripts/audit-outbound.sh · prose · downgraded · axios
Sets world-executable permissions
scripts/harden-workspace.sh · prose · downgraded · chmod 700
References tunneling service
scripts/scan-skills.sh · prose · downgraded · ngrok
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class A/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.
Is this flag fair?
Thanks — recorded.