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 Bash tool 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 Read tool and script execution via the Bash tool.
  • Sanitization: No sanitization or validation of the ingested document content is described.
Audit Metadata
Risk Level
SAFE
Analyzed
May 10, 2026, 04:23 AM
Security Audit — agent-trust-hub — prd-discuss