ClawAudit verdict
memory-core-plus
The skill provides a clear description of its purpose and usage, with no evidence of malicious or deceptive behavior.
⚠ 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.
Findings (4)
<script> tag in markdown — potential code injection
index.test.ts · prose · downgraded · <script>
Prompt injection — tries to override agent instructions
index.test.ts · prose · downgraded · Ignore all previous instructions
Possible prompt injection — attempts to redefine agent identity
index.test.ts · prose · downgraded · you are now
Popular HTTP library — network access
index.test.ts · prose · downgraded · Got
Permissions & capabilities
No declared permissions — minimal attack surface.
Is this flag fair?
Thanks — recorded.