jackyshen-consult-problem
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied topics and case studies to generate structured consultancy content, creating a surface for indirect prompt injection. \n
- Ingestion points: User input requested in Step 1 (Topic) and Step 2 (Specific cases) in SKILL.md. \n
- Boundary markers: None identified in the prompt instructions to delimit user-provided data. \n
- Capability inventory: No file-write, network, or subprocess capabilities are present in the skill; it only performs text generation. \n
- Sanitization: No explicit sanitization or escaping of user input is performed before interpolation into the analysis workflow.
Audit Metadata