watching-videos

Pass

Audited by Gen Agent Trust Hub on Aug 22, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The watch-skill doctor command facilitates the automated download and installation of system dependencies, specifically ffmpeg and yt-dlp.- [COMMAND_EXECUTION]: The skill uses the Bash tool to execute watch-skill CLI commands, where user-supplied inputs such as URLs and local file paths are directly interpolated into the command string.- [PROMPT_INJECTION]: The skill is susceptible to Indirect Prompt Injection because it processes and interprets untrusted text data extracted from video content.
  • Ingestion points: External URLs, local video files, OCR text extracted from video frames, and video transcripts in SKILL.md.
  • Boundary markers: Absent. The instructions do not provide delimiters or specific warnings to the agent to ignore embedded instructions within the analyzed video content.
  • Capability inventory: The skill possesses the ability to execute shell commands via Bash and read local files.
  • Sanitization: No sanitization or validation logic is specified for the text content derived from OCR or transcripts before the agent processes it.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 22, 2026, 12:04 AM
Security Audit — agent-trust-hub — watching-videos