cawplan-product-insights
Pass
Audited by Gen Agent Trust Hub on Oct 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources that could contain embedded instructions.
- Ingestion points: Data returned by
cawplan analytics get(user feedback categories) andcawplan critical list(active blockers and incidents) inSKILL.md. - Boundary markers: The instructions do not specify the use of delimiters or provide warnings to ignore embedded instructions within the fetched data.
- Capability inventory: The skill is configured to use the
Bashtool to executecawplanCLI commands. - Sanitization: The workflow does not describe any sanitization or validation of the external content before it is summarized by the agent.
Audit Metadata