legitimate-interest

Pass

Audited by Gen Agent Trust Hub on Jul 30, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it ingests untrusted user data to generate assessment reports.
  • Ingestion points: User-provided descriptions of processing activities, controller identities, and data subject relationships are gathered during the 'Information Gathering' phase in SKILL.md.
  • Boundary markers: The instructions do not specify any boundary markers or delimiters for user input, nor do they include 'ignore embedded instructions' warnings.
  • Capability inventory: The skill uses a docx tool to generate Word documents and the search tool for regulatory research as described in SKILL.md.
  • Sanitization: There are no explicit sanitization, validation, or escaping procedures defined for the data processed during the assessment flow.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 30, 2026, 07:33 PM
Security Audit — agent-trust-hub — legitimate-interest