scope-product-release
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data that could contain malicious instructions designed to influence agent behavior.
- Ingestion points: Customer evidence, project details, triage, linked tickets, documents, and prior decisions.
- Boundary markers: The prompt does not define explicit delimiters or use 'ignore embedded instructions' warnings for the data it processes.
- Capability inventory: The skill searches organization skills and records using the BuildBetter MCP; it includes a safety guardrail that prohibits altering project records without explicit approval.
- Sanitization: No sanitization, escaping, or validation of the external content is described in the skill workflow.
Audit Metadata