pir
Pass
Audited by Gen Agent Trust Hub on Jul 25, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from the conversation history to generate reports, creating a surface for indirect prompt injection.
- Ingestion points: Reads conversation history in Phase 0 of
SKILL.md. - Boundary markers: No explicit instructions to the agent to ignore instructions embedded within the conversation history were found.
- Capability inventory: The skill uses
mkdir,date, and performs file-write operations to the local file system (documented in Phases 3 and 4). - Sanitization: No explicit sanitization or validation of the extracted information before interpolation into the markdown template or
CLAUDE.mdwas identified.
Audit Metadata