crm-segmentation-planner
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill consists entirely of static Markdown documentation and YAML configuration. No executable scripts, binaries, or dynamic code execution patterns are present in any of the analyzed files.
- [INDIRECT_PROMPT_INJECTION]: The skill defines an ingestion surface for user-provided data relating to CRM goals and datasets.
- Ingestion points: User-supplied arguments defined in SKILL.md including data available, lifecycle goals, and messaging use cases.
- Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the instructions to separate user data from the system prompt.
- Capability inventory: Tool usage is restricted to Read and Write as specified in the YAML frontmatter.
- Sanitization: No validation or sanitization of external input is implemented, which is standard for advisory skills.
Audit Metadata