leverage-and-response-design
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user data via multiple input fields without using delimiters or explicit 'ignore instructions' warnings.
- Ingestion points: SKILL.md (inputs: systems_analysis, proposed_action, age_range, scope_constraints, context).
- Boundary markers: Absent. User input is interpolated directly into the system prompt without markers like triple quotes or XML tags.
- Capability inventory: Safe in SKILL.md. The skill has no tool-use, file-write, network, or execution capabilities across any instructions.
- Sanitization: Absent. There is no evidence of input validation or escaping before interpolation.
Audit Metadata