yt-plan

Pass

Audited by Gen Agent Trust Hub on Oct 29, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists entirely of natural language instructions for planning YouTube content and contains no executable code or automated scripts.
  • [DATA_EXPOSURE]: The skill instructs the agent to search for and read style guidelines in the current project or a hidden directory (~/.youtube-agent-skill/voice.md). This access is limited to creative context and does not target sensitive system credentials or personal data for exfiltration.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests external content samples and style files to determine the creator's "voice." While this is an ingestion point for untrusted data, the skill possesses no capabilities (such as network access or shell execution) that would allow for an exploitable attack.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 29, 2026, 06:12 PM