review-contract
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function involves processing untrusted external data from contract documents (PDF/docx) and EDO platforms, which presents a surface for indirect prompt injection.
- Ingestion points: Contract text ingested from local file paths or EDO document IDs (Diadoc/SBIS) as specified in SKILL.md.
- Boundary markers: The skill does not define specific delimiters or instructional guards to separate analyzed text from agent instructions.
- Capability inventory: The skill possesses the ability to read local files, interact with EDO systems, and generate new document files.
- Sanitization: No explicit sanitization or filtering of the document content is described in the workflow.
Audit Metadata