youtube-scripting

Pass

Audited by Gen Agent Trust Hub on May 12, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through the processing of untrusted video outlines.
  • Ingestion points: Video outlines provided by the user or fetched from previous steps (SKILL.md, Step 1).
  • Boundary markers: The instructions lack explicit delimiters or instructions for the agent to ignore potentially malicious embedded commands within the ingested outline.
  • Capability inventory: The agent has instructions to read local reference documents (voice-personality.md, icp-ideal-customer-profile.md, ben-profile-background.md) and write files to the file system (Step 5).
  • Sanitization: There is no evidence of input validation, escaping, or sanitization of the content within the video outline before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
May 12, 2026, 03:09 AM