plan-zoom-integration
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill uses the
$ARGUMENTSvariable to ingest user integration ideas, which it then uses to create implementation plans. This is a common surface for indirect prompt injection where data could influence agent behavior. - Ingestion points:
$ARGUMENTSinSKILL.md. - Boundary markers: None identified in the prompt text.
- Capability inventory: The skill is restricted to text generation for planning and recommends other skills for setup actions.
- Sanitization: No input sanitization or validation is implemented.
- [NO_CODE]: The skill file contains only markdown instructions and YAML metadata without any accompanying scripts, binary files, or shell commands.
Audit Metadata