stophy-video

Pass

Audited by Gen Agent Trust Hub on Nov 7, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill uses npx @stophy/cli@latest to download and execute code from the NPM registry. This package is the official CLI associated with the skill author.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources like YouTube and TikTok.
  • Ingestion points: Transcripts, comments, and profile data retrieved from social media URLs via the stophy scrape command.
  • Boundary markers: The instructions do not define clear delimiters to separate the scraped data from agent instructions.
  • Capability inventory: The skill utilizes the stophy CLI and general Bash execution to fetch and save data.
  • Sanitization: No explicit sanitization or filtering of external content is described in the skill configuration.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 7, 2026, 09:19 PM