mino-problem-framing
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted external data, such as specifications and existing code, to generate structured analysis artifacts (Problem Frames and Context Packets).
- Ingestion points: The workflow in
SKILL.mdingests source data including technical specifications, observations, and raw code. - Boundary markers: The instructions do not define specific delimiters to isolate untrusted input data from the reasoning process.
- Capability inventory: No dangerous capabilities, such as subprocess execution, network operations, or unauthorized file system access, were detected in the skill definitions.
- Sanitization: The skill does not implement explicit sanitization or filtering for the data it processes.
- [SAFE]: The skill uses localized references and standard YAML schemas to perform logic-based requirement gathering and information structuring, which is a benign and intended use case.
Audit Metadata