release-readiness-assessment
Pass
Audited by Gen Agent Trust Hub on Nov 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill incorporates external data into its instructions, creating a surface for indirect prompt injection.
- Ingestion points: The
$ARGUMENTSvariable inSKILL.mdallows untrusted user input to be interpolated into the agent's role-play context. - Boundary markers: No delimiters or protective instructions are used to isolate the external data from the agent's core instructions.
- Capability inventory: No specific tool definitions or scripts are included in the skill; however, the agent's default capabilities remain available.
- Sanitization: There is no evidence of sanitization or validation of the interpolated data.
Audit Metadata