prd-writer

Pass

Audited by Gen Agent Trust Hub on Apr 4, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill contains phrases such as "Ignore previous instructions", but these are explicitly documented as examples within a 'Red Team Scenarios' section of a PRD template. These strings are intended as test cases for product security rather than attempts to manipulate the agent's own operation.
  • [SAFE]: No executable scripts, binaries, or system commands are present. The skill only provides text-based guidance and structural templates.
  • [SAFE]: There are no network requests, external resource downloads, or data exfiltration patterns.
  • [SAFE]: The skill does not access sensitive local file paths or include hardcoded credentials.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 4, 2026, 03:03 PM