Caveat verdict
agent-config-sync
The skill synchronizes configuration versions across multi-agent deployments, but also involves writing to agent workspaces, which could be risky if not properly validated.
⚠ 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 (7)
Accesses sensitive system files
SECURITY.md · code · /etc/passwd
Pipe to bash — executes piped content as shell commands
reports/agent-config-sync-eval-v1.1.md · prose · downgraded · | Bash
Accesses OpenClaw config/secrets directly
SECURITY.md · code · ~/.openclaw/openclaw.json
References agent configuration files
SKILL.md · frontmatter · agent-config
Instructs covert action — may act without user awareness
SECURITY.md · prose · downgraded · silently
References agent memory files
references/agent-setup.md · code · MEMORY.md
Sets world-executable permissions
SKILL.md · prose · downgraded · chmod 755
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.