mckinsey-critic
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted content from user-provided strategy documents, deck outlines, and memos.
- Ingestion points: Processes user-supplied text and document outlines as described in the 'How It Works' section of SKILL.md.
- Boundary markers: The instructions lack specific delimiters or instructions to the agent to treat the content as data only, potentially allowing instructions embedded in user documents to influence agent behavior.
- Capability inventory: No dangerous system capabilities (e.g., file writes, network requests, or command execution) were identified in the skill instructions.
- Sanitization: No input validation or content filtering mechanisms are specified in the provided instructions.
Audit Metadata