ClawAudit verdict

memory-graph

agent-memory-graph

88
🟢 Trusted
Low risk — reviewed by ClawAudit, behavior matches stated purpose

The Memory Graph skill stores agent knowledge in a file-based personal knowledge graph. It seems designed for legitimate knowledge management and retrieval purposes across agent sessions.

⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.

Automated static analysis — not a human review. ClawAudit flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.

40
security
90
transparency
70
maintenance

Findings (5)

Pattern match high

<script> tag in markdown — potential code injection

scripts/visualize.js · prose · downgraded · <script

Pattern match medium

References agent memory files

references/setup.md · code · MEMORY.md

Pattern match medium

References child_process — can spawn system processes

scripts/commit.js · prose · downgraded · child_process

Pattern match medium

Uses exec() — may execute shell commands

scripts/lint.js · prose · downgraded · exec(

Pattern match medium

Instructs covert action — may act without user awareness

scripts/suggest-backfill.js · prose · downgraded · silently

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class D). 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?

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