video2ctx-api

Warn

Audited by Gen Agent Trust Hub on Aug 18, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONREMOTE_CODE_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the agent to install the @video2ctx/cli package globally from the public npm registry.
  • [COMMAND_EXECUTION]: The agent is directed to use shell commands for package installation (npm install --global) and for executing data retrieval tasks (video2ctx).
  • [REMOTE_CODE_EXECUTION]: By installing and running a global CLI tool, the skill executes code from a remote source on the host system.
  • [INDIRECT_PROMPT_INJECTION]: The skill fetches and processes external content such as YouTube transcripts and comments which can be controlled by third parties. 1. Ingestion points: Transcripts and comments retrieved via the video2ctx transcript and video2ctx api commands. 2. Boundary markers: No explicit delimiters or safety instructions are provided to the agent for handling the retrieved content. 3. Capability inventory: The agent has the ability to execute shell commands and install software globally. 4. Sanitization: There is no evidence of sanitization or filtering of the external data before processing.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 18, 2026, 11:05 AM