cs-tool-selection
Pass
Audited by Gen Agent Trust Hub on Nov 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external files provided via arguments for segmentation and health scoring data. This creates a surface for indirect prompt injection if the files contain malicious instructions meant to influence the AI's generation of the framework. However, the skill lacks any capabilities (such as network access or shell execution) to perform dangerous actions based on such an injection. * Ingestion points: Files passed to the --segmentation and --health-score arguments. * Boundary markers: None explicitly mentioned in the instructions to isolate external content. * Capability inventory: None; the skill is purely instructional and does not include scripts or executables. * Sanitization: No validation or sanitization of the input file content is specified.
Audit Metadata