Caveat verdict
github-memory-sync
The skill explicitly backs up high-sensitivity files including USER.md and MEMORY.md to a GitHub repository via a personal access token, creating genuine risk of sensitive user data exposure if the repository is not strictly private.
⚠ 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 (4)
Possible hardcoded credential
SKILL.md · code · TOKEN="ghp_xxxxxxxxxxxxxxxxx
apt-get install — installs system packages
CRON.md · code · apt-get install
References agent memory files
SKILL.md · frontmatter · MEMORY.md
Accesses OpenClaw config/secrets directly
SKILL.md · prose · downgraded · ~/.openclaw/openclaw.json
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class B/F). 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_accessagent_memory Is this flag fair?
Thanks — recorded.