goal-definition
Pass
Audited by Gen Agent Trust Hub on Mar 14, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input and existing project artifacts to generate new documentation.
- Ingestion points: Raw user ideas and the 'context-map.md' file (SKILL.md).
- Boundary markers: The skill lacks explicit delimiters or warnings to ignore embedded instructions in the ingested data.
- Capability inventory: The skill is capable of writing 'goal-definition.md' to the local file system (SKILL.md, Step 7).
- Sanitization: No explicit sanitization or escaping of the input data is performed before interpolation into the generated markdown file.
Audit Metadata