perf-investigation-logger
Pass
Audited by Gen Agent Trust Hub on Mar 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill performs routine logging operations within a restricted state directory (AI_STATE_DIR). No malicious patterns, command executions, or network operations were identified.
- [PROMPT_INJECTION]: The skill records unvalidated user input verbatim, creating a surface for indirect prompt injection if the resulting logs are processed by other agents.
- Ingestion points: User quotes and evidence pointers processed via instructions in SKILL.md.
- Boundary markers: Employs markdown structure but lacks specific delimiters to isolate user instructions.
- Capability inventory: Appends content to files located within the AI_STATE_DIR (SKILL.md).
- Sanitization: No input validation or escaping is performed on the user-provided strings.
Audit Metadata