dev-swarm-stage-prd

Pass

Audited by Gen Agent Trust Hub on Mar 13, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it ingests data from local project files to generate new documentation.
  • Ingestion points: ideas.md and markdown files within folders 00-init-ideas through 04-tech-research (SKILL.md).
  • Boundary markers: Absent; the instructions do not include specific delimiters or warnings to ignore instructions embedded within the ingested files.
  • Capability inventory: File system read access for project context and file write access for creating PRD documentation and diagrams (SKILL.md).
  • Sanitization: Absent; the skill lacks explicit validation or filtering mechanisms for the content being processed.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 13, 2026, 08:28 PM