community-management
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [NO_CODE]: The skill references several script files (src/leaveAllCommunities.js, src/joinCommunities.js, src/engagementBooster.js, and src/audienceDemographics.js) that are not provided in the source package. This lack of source code prevents a full security review of the actions intended for execution in the browser console.
- [INDIRECT_PROMPT_INJECTION]: The described scripts scrape untrusted data from the X platform. Ingestion points: community names and descriptions scraped from x.com. Boundary markers: none described in the instructions. Capability inventory: DOM manipulation (clicking buttons), navigation between pages, and session storage access. Sanitization: the skill description does not specify any sanitization or validation for the scraped community text before it is processed by the matching logic.
Audit Metadata