mckinsey-strategist
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 potentially untrusted user data (business scenarios and corporate data) which creates a surface for indirect prompt injection. While the skill lack capabilities like network access or file system writes to facilitate an attack, it lacks specific boundary markers or instructions to ignore embedded commands within the analyzed text.
- Ingestion points: User-provided business scenarios processed via trigger phrases in
SKILL.md. - Boundary markers: None identified in the prompt templates.
- Capability inventory: None; the skill is limited to text analysis and formatting within the agent context.
- Sanitization: None; the skill performs direct interpolation of user context into analytical frameworks.
Audit Metadata