cs-plan-builder
Pass
Audited by Gen Agent Trust Hub on Nov 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external client feedback and NPS responses, which constitutes a potential injection surface for untrusted data.
- Ingestion points: Raw feedback material, including NPS answers and review notes, processed in 'Mode FEEDBACK' as described in SKILL.md.
- Boundary markers: The instructions do not define specific delimiters or instructions to treat ingested feedback data as untrusted or to ignore embedded commands.
- Capability inventory: The skill has the ability to write local markdown files, create Notion pages, and pass summarized data to other skills such as 'upsell-mapper'.
- Sanitization: No sanitization, filtering, or escaping of the client-provided feedback is specified; the skill is instructed to quote verbatim.
Audit Metadata