video2ctx-platform
Pass
Audited by Gen Agent Trust Hub on Nov 3, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requests the installation of the
@video2ctx/clipackage via npm. This is a vendor-owned CLI tool required for communicating with the video2ctx platform. - [COMMAND_EXECUTION]: The skill frequently executes CLI commands such as
video2ctx whoami,video2ctx auth login, andvideo2ctx apito perform account checks and data operations. - [INDIRECT_PROMPT_INJECTION]: The skill processes external data that could contain malicious instructions.
- Ingestion points: Transcripts, comments, and search results are fetched from YouTube via the platform's API (described in
references/hosted-data.md). - Boundary markers: There are no explicit instructions or delimiters used to separate untrusted YouTube content from the agent's internal reasoning or system instructions.
- Capability inventory: The agent has the capability to execute shell commands and perform state-changing API operations (POST/PATCH/DELETE) on the platform (described in
references/monitoring.md). - Sanitization: No specific sanitization or escaping mechanisms are mentioned for the fetched data.
Audit Metadata