quality-documentation-manager

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion and review of external technical and regulatory documentation, which represents a potential surface for indirect prompt injection.\n
  • Ingestion points: SKILL.md specifies tasks involving the review of EU MDR, FDA, and manufacturing documentation.\n
  • Boundary markers: The provided instructions do not include specific delimiters or warnings to ignore instructions embedded within the reviewed documents.\n
  • Capability inventory: The skill references scripts for change control automation and regulatory validation, suggesting the agent may act on findings from the document reviews.\n
  • Sanitization: No evidence of content sanitization or instruction filtering for external inputs is present in the provided skill components.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 03:47 PM
Security Audit — agent-trust-hub — quality-documentation-manager