doc-ears-audit

Pass

Audited by Gen Agent Trust Hub on Mar 2, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by design, as its primary purpose is to process and audit untrusted external data (EARS documentation files). \n
  • Ingestion points: Reads EARS requirement files from local paths (e.g., docs/03_EARS/...). \n
  • Boundary markers: The execution contract does not specify the use of delimiters or 'ignore embedded instructions' markers when passing documentation content to sub-skills. \n
  • Capability inventory: The skill orchestrates other local skills (doc-ears-validator, doc-ears-reviewer, doc-ears-fixer) and performs file-write operations to save audit reports. \n
  • Sanitization: No explicit sanitization or filtering of the content within the EARS files is documented prior to processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 2, 2026, 06:55 AM