breakdown-plan
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from local file paths to generate project planning artifacts.
- Ingestion points: The skill reads input from Feature PRD, Technical Breakdown, and Implementation Plan markdown files located in the
/docs/ways-of-work/plan/directory. - Boundary markers: The prompt instructions do not specify the use of delimiters or 'ignore embedded instructions' warnings when interpolating the content of these files into the generation process.
- Capability inventory: The skill is capable of generating structured markdown files and GitHub Action YAML templates.
- Sanitization: There is no evidence of content validation or sanitization for the data retrieved from the local markdown files.
Audit Metadata