skill-work-slicing
Pass
Audited by Gen Agent Trust Hub on Sep 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content such as plans and specifications which could contain malicious instructions designed to manipulate the ticket generation process.
- Ingestion points: The skill accepts plans, specifications, and conversation history as input for decomposition (SKILL.md).
- Capability inventory: The skill uses the 'bd' tool to create tickets, the 'gh' CLI for GitHub issues, and writes roadmap notes to 'docs/roadmaps/' (SKILL.md).
- Boundary markers: The instructions do not define explicit boundary markers or delimiters to isolate untrusted input data.
- Sanitization: The skill does not specify validation or sanitization mechanisms for content before it is filed into trackers or written to files.
Audit Metadata