groove-utilities-memory-log-monthly
Pass
Audited by Gen Agent Trust Hub on Mar 10, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: Indirect Prompt Injection Surface. The skill processes daily memory logs which may contain untrusted data that could influence the agent during the roll-up process.
- Ingestion points: Reads file content from /daily/*.md.
- Boundary markers: No explicit delimiters are used to wrap the ingested content.
- Capability inventory: Access to file system tools (Read, Write, Edit, Glob, Grep) and Bash(git:*).
- Sanitization: The instructions do not include steps to sanitize or filter ingested data.
Audit Metadata