rfi-preparer

Pass

Audited by Gen Agent Trust Hub on Mar 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: Indirect Prompt Injection Surface
  • Ingestion points: The skill reads project data from multiple JSON files, including plans-spatial.json, specs-quality.json, project-config.json, directory.json, rfi-log.json, submittal-log.json, and procurement-log.json (SKILL.md).
  • Boundary markers: There are no explicit delimiters or instructions provided to the agent to ignore instructions embedded within these data sources.
  • Capability inventory: The skill has the capability to write to project logs (rfi_log, submittal_log), draft emails, and generate HTML/PDF documents (SKILL.md, rfi-template.md, transmittal-template.md).
  • Sanitization: There is no mention of sanitization or validation of the ingested data before it is transformed into formal technical language or populated into document templates.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 17, 2026, 09:54 PM
Security Audit — agent-trust-hub — rfi-preparer