linkedin-content
Pass
Audited by Gen Agent Trust Hub on Mar 17, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
infshCLI via a restricted Bash environment to run research and media apps. This usage is consistent with the skill's documented purpose. - [EXTERNAL_DOWNLOADS]: References the addition of other skills within the vendor's ecosystem using the
npxcommand, which is the platform's standard extension mechanism. - [PROMPT_INJECTION]: The skill includes a research step that ingests external search results. While this is a surface for indirect prompt injection, it is handled as a standard research feature and does not escalate the risk profile.
Audit Metadata