handbook-updates
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes proposed handbook changes, creating a surface for potential indirect prompt injection if the source data is untrusted.
- Ingestion points: Proposed regulatory changes, new expressions, and justifications are read into the agent context in Workflow Step 1 (SKILL.md).
- Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands within the input text.
- Capability inventory: The skill possesses file read capabilities for existing handbooks and write capabilities for matter-specific output folders.
- Sanitization: No sanitization, validation, or filtering of the ingested handbook text is specified.
Audit Metadata