agent-memory
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill defines a structured approach for an agent to maintain project memory by reading and writing to files in the docs/agent-memory/ directory.
- [INDIRECT_PROMPT_INJECTION]: The skill reads data from repository files which constitutes a theoretical ingestion point for untrusted content. However, this is an expected behavior for repository context management and is mitigated by specific usage rules and a narrow file scope.
- [DATA_EXPOSURE]: The skill instructions include a mandatory safety rule to not record secrets (tokens, keys, passwords), which prevents accidental credential exposure in version-controlled files.
Audit Metadata