Caveat verdict

agent-memory-setup

agent-memory-setup-qmd

88
🟢 Trusted
No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.

Sets up a local 3-tier memory system using local scripts and the OpenClaw CLI; all operations are local with no external data egress.

⚠ 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.

43
security
50
transparency
70
maintenance

Permission integrity

Installs packages at runtime — transitive dependencies are not auditable

package_install

Accesses agent memory/configuration files

agent_memory

Findings (4)

Pattern match high

Accesses OpenClaw config/secrets directly

SKILL.md · code · ~/.openclaw/openclaw.json

Pattern match high

Writes to SKILL.md — self-modifying skill

eval_prompts.md · prose · downgraded · SKILL.md or script explicitly handles existing files (skip/preserve, not overwri

Pattern match medium

References agent memory files

SKILL.md · code · MEMORY.md

Pattern match low

Popular HTTP library — network access

eval_round2.md · prose · downgraded · got

Permissions & capabilities

Requires 2 system binaries.

package_installagent_memory

Is this flag fair?

Check another skill Browse the registry Auditing your own skills or configs? Use the API