contract-review
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- Indirect Prompt Injection Surface: The skill is designed to ingest and analyze untrusted external data in the form of contracts from Gmail, DocuSign, and user uploads. There is a potential consideration that these documents could contain adversarial text intended to influence the agent's analysis.
- Ingestion points: Workflow Step 1 in
SKILL.mdidentifies Gmail attachments, DocuSign envelopes, and local files as primary data sources. - Boundary markers: The instructions do not explicitly define technical delimiters or specific 'ignore embedded instructions' prompts for the ingested text.
- Capability inventory: The skill possesses the ability to read external content and generate output via the
docxexport tool and chat interface. - Sanitization: The skill does not perform explicit sanitization of the contract text before analysis, relying instead on its internal 8-category framework to guide the agent's response.
Audit Metadata