specialized-document-generator
Pass
Audited by Gen Agent Trust Hub on Nov 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data to generate documents, which is a surface for indirect prompt injection.
- Ingestion points: User-provided data as referenced in the mission statement of
SKILL.md("Accept data as input, generate documents as output"). - Boundary markers: None. The skill lacks instructions to delimit or ignore instructions that may be hidden in the input data.
- Capability inventory: The skill utilizes code generation and execution to create multiple file types (PDF, PPTX, XLSX, DOCX) on the local system.
- Sanitization: No sanitization or validation of the input data is provided.
Audit Metadata