wds-8-product-evolution
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the analysis of existing products by ingesting external data such as business goal documents, user personas, research PDFs, live product URLs, and source code. This creates a vulnerability surface where instructions embedded in these untrusted sources could influence the agent's behavior.
- Ingestion points: The skill processes external content through the
data/existing-product-guide.md(which requests uploads of business goals and user research) andworkflow-analyze.md(which scans live URLs and codebases). - Boundary markers: The instructions do not explicitly mandate the use of delimiters or specific warnings to ignore instructions within the processed data.
- Capability inventory: The skill has significant capabilities, including file system writes for creating documentation and templates, and the execution of shell commands like Git and the GitHub CLI (
gh). - Sanitization: There are no documented mechanisms for filtering or sanitizing content extracted from these external files before they are incorporated into agent-generated design specifications or pull request bodies.
Audit Metadata