decision-brief
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied text regarding decision details, constraints, and options by interpolating them into a prompt template. Although this represents an ingestion surface for external data, the skill has no access to tools, network operations, or the file system, which prevents any meaningful exploitation.
- Ingestion points: User-provided text for decision descriptions, constraints, and options in SKILL.md.
- Boundary markers: Absent; user input is placed directly into the prompt structure.
- Capability inventory: None. The skill does not utilize any tools, scripts, or system commands.
- Sanitization: No sanitization or escaping of user input is performed.
- [SAFE]: The skill contains only natural language instructions and a prompt template. It does not include executable code, external dependencies, or sensitive data access.
Audit Metadata