fec-source-driven-development

Pass

Audited by Gen Agent Trust Hub on Jun 24, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: No malicious patterns detected. The skill provides legitimate instructional guidelines for evidence-based development and local knowledge retrieval.
  • [PROMPT_INJECTION]: The skill processes untrusted content from the project repository and a designated knowledge directory (including Markdown, PDF, and Excel files), creating a surface for indirect prompt injection.
  • Ingestion points: Procedures for reading repository configuration, templates, and the knowledge/ directory.
  • Boundary markers: Absent. There are no instructions for the agent to use delimiters or ignore instructions embedded within the data it retrieves.
  • Capability inventory: The skill implies capabilities for file system access and executing commands for testing and build verification (unit tests, E2E, build checks).
  • Sanitization: Absent. No specific validation or escaping is prescribed for the retrieved content.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 24, 2026, 04:37 PM