adopt
Pass
Audited by Gen Agent Trust Hub on Nov 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill exhibits a vulnerability surface for indirect prompt injection by ingesting and processing untrusted data from project files.
- Ingestion points: The skill reads existing artifacts including GDD files (
design/gdd/), ADR files (docs/architecture/adr-*.md), stories (production/epics/**/*.md), and technical preferences (.claude/docs/technical-preferences.md). - Boundary markers: The instructions do not define explicit delimiters or instructions to ignore embedded prompts when reading these external files.
- Capability inventory: The skill has access to
Read,Glob,Grep,Write, andAskUserQuestiontools. It can generate persistent files in the project directory based on the audit results. - Sanitization: There is no explicit sanitization or validation of the content found within the Markdown files beyond checking for expected headings and status fields.
Audit Metadata