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
docxtool to generate Word documents and thesearchtool for regulatory research as described inSKILL.md. - Sanitization: There are no explicit sanitization, validation, or escaping procedures defined for the data processed during the assessment flow.
Audit Metadata