citation-hygiene
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external documents provided by the user to perform citation audits, which introduces a potential surface for indirect prompt injection.
- Ingestion points: External documents and data sources provided by the user under the "Required Inputs" section in
SKILL.md. - Boundary markers: The skill does not explicitly define delimiters or specific safety instructions to ignore embedded commands within the processed documents.
- Capability inventory: The skill is restricted to text analysis and generation; it does not contain any instructions for subprocess execution, file-system writes, or network operations.
- Sanitization: No explicit sanitization or filtering of the input document content is described.
Audit Metadata