NYC
skills/johnlindquist/claude/memory/Gen Agent Trust Hub

memory

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS] (LOW): The skill requires the installation of the 'basic-memory' package via pip. As this is not from a listed trusted source, users should verify the package before installation. (File: SKILL.md)
  • [PROMPT_INJECTION] (LOW): Vulnerable to indirect prompt injection. The skill ingests data from external storage (notes) into the agent's context using 'read-note', 'search-notes', and 'build-context'. If these notes contain adversarial instructions, they could influence agent behavior. (File: SKILL.md)
  • Ingestion points: Commands like 'read-note' and 'build-context' fetch note content.
  • Boundary markers: None present to delimit fetched content from system instructions.
  • Capability inventory: CLI interaction with a local database.
  • Sanitization: No explicit sanitization or validation of note content is described.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 05:38 PM