media-studio
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill interacts with external data from the X platform (media library metadata, analytics), creating a surface for indirect prompt injection if that data contains malicious instructions. * Ingestion points: Data is read from the studio.x.com interface via listMedia() and viewAnalytics() in SKILL.md. * Boundary markers: None identified in the documentation. * Capability inventory: Includes media uploading, deletion, navigation, and analytics retrieval. * Sanitization: No mention of data sanitization or validation of the content retrieved from the web interface.
- [NO_CODE]: The skill references script files src/mediaStudio.js and src/videoCaptions.js which contain the executable logic, but these files were not included in the provided content, preventing a full security audit of the implementation.
Audit Metadata