contract-analysis
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill retrieves and analyzes external contract text from ServiceNow attachments, which represents a potential ingestion point for malicious instructions intended to influence the agent's summary.
- Ingestion points: Contract document content accessed via
sys_attachmentrecords in Step 2. - Boundary markers: The skill provides a structured analysis framework (Steps 3 and 4) but does not explicitly use boundary markers or instructions to ignore embedded commands in the contract text.
- Capability inventory: The skill can create legal tasks, update contract records, and add work notes to cases within ServiceNow.
- Sanitization: No specific sanitization or filtering of the document text is mentioned prior to the analysis step.
Audit Metadata