oh-pdd-prd-analysis
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted PRD (Product Requirement Document) files provided by users, which creates a potential surface for indirect prompt injection attacks.\n
- Ingestion points: The
scripts/prd_analysis.pyscript is designed to read and parse the full content of local files specified by the user as PRD documents.\n - Boundary markers: The skill's instructions and the provided report template (
assets/report_template.md) do not include specific boundary markers or 'ignore' instructions to encapsulate processed text and prevent the agent from being influenced by instructions embedded within the PRD content.\n - Capability inventory: The script
scripts/prd_analysis.pyhas the capability to read from the local file system (read_text) and write analysis reports to a user-specified output path (write_text).\n - Sanitization: No sanitization or escaping is performed on the text extracted via regular expressions before it is interpolated into the final Markdown or JSON reports, allowing any embedded control text to persist in the skill's output.
Audit Metadata