utility
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill framework includes ingestion points for external data that could theoretically contain malicious instructions.
- Ingestion points: The observations and actions_taken fields in modules/state-builder.md ingest data from tool outputs and previous agent steps into the orchestration context.
- Boundary markers: No explicit boundary markers or instructions to ignore embedded commands within tool outputs are provided in the modules.
- Capability inventory: The framework manages powerful actions including tool_call, delegate, and retrieve.
- Sanitization: No specific sanitization or filtering of observations is defined before they are used to estimate utility scores.
- [SAFE]: No other security issues were detected. The skill is purely instructional and does not contain executable code, external dependencies, or network operations.
Audit Metadata