specialist-data-report-distribution-agent
Pass
Audited by Gen Agent Trust Hub on Aug 15, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill incorporates untrusted user input directly into a sub-agent prompt template, which is a common pattern that creates a surface for indirect instructions.
- Ingestion points: User input variable
{the user's question}inSKILL.md. - Boundary markers: Absent; the input is not enclosed in delimiters or accompanied by isolation instructions.
- Capability inventory: The skill is capable of spawning sub-agents via the
Agenttool. - Sanitization: No sanitization or filtering is performed on the user data.
Audit Metadata