youtube-packaging

Pass

Audited by Gen Agent Trust Hub on Nov 22, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill requires the agent to ingest and process untrusted external content. \n- Ingestion points: Step 1 in SKILL.md instructs the agent to search YouTube for a topic and record top results, including titles and patterns. This content is controlled by third-party YouTube creators and could contain malicious instructions. \n- Boundary markers: There are no explicit instructions for the agent to use delimiters or ignore instructions embedded within the search results. \n- Capability inventory: The skill's primary function is content generation. It has no capabilities for command execution or sensitive file access. A dedicated 'Guardrails' section explicitly forbids the agent from uploading or changing live video settings. \n- Sanitization: The skill lacks instructions for sanitizing or validating the data retrieved from external searches.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 22, 2026, 12:56 AM