prd-discuss
Pass
Audited by Gen Agent Trust Hub on May 10, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
Bashtool to execute a local Python dispatcher script (prd-command-dispatch.py) to handle its logic. This is standard behavior for tool-integrated skills. - [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface as it is designed to read and process external project documentation.
- Ingestion points: Project context and decision records (
CONTEXT.md,docs/adr/). - Boundary markers: None specified in the instructions to isolate processed content.
- Capability inventory: File system access via the
Readtool and script execution via theBashtool. - Sanitization: No sanitization or validation of the ingested document content is described.
Audit Metadata