project-tickets
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from a specification file to generate vertical slices and tickets.\n
- Ingestion points: Reads content from .scratch//spec.md or a path provided as an argument in SKILL.md and WORKFLOW.md.\n
- Boundary markers: Absent. No specific delimiters or "ignore" instructions are used to isolate the specification content from the agent's instructions.\n
- Capability inventory: The skill has the ability to create multiple markdown files in the .scratch/ directory and modify the input specification file by appending approval comments, as documented in WORKFLOW.md.\n
- Sanitization: Absent. The skill uses the content of the SPEC to draft titles, descriptions, and acceptance criteria without explicit sanitization or validation of the input data.
Audit Metadata