requirements-workshop-v3

Pass

Audited by Gen Agent Trust Hub on Jul 4, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest data from external project sources, including code, documentation, and configurations (Step 5 in SKILL.md). This data is used to generate new project files in the workplace/ directory. This creates a surface for indirect prompt injection where untrusted content in the project files could theoretically influence the agent's behavior during the requirement phase.
  • Ingestion points: The skill reads project documents, code, pages, interfaces, data, configurations, and CONTEXT.md (SKILL.md, Step 5).
  • Boundary markers: There are no specific delimiters or instruction-ignore warnings defined when processing this external context.
  • Capability inventory: The skill has file-write capabilities restricted to the project root (ROADMAP.md) and the workplace/ directory (SKILL.md, Step 1, 3, 4, 6).
  • Sanitization: No explicit sanitization or filtering of the ingested external content is described.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 4, 2026, 01:27 PM
Security Audit — agent-trust-hub — requirements-workshop-v3