youtube-ads

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill contains only instructional text and reference tables for YouTube ad formats, creative guidelines, and targeting strategies. No executable code or suspicious patterns were found.
  • [INDIRECT_PROMPT_INJECTION]: The skill has a potential surface for indirect prompt injection as it instructs the agent to ingest external project context files (.claude/project-context.md or .cursor/project-context.md).
  • Ingestion points: Reads project context files in the SKILL.md file.
  • Boundary markers: None present.
  • Capability inventory: None; the skill does not use subprocesses, network operations, or file-writing tools.
  • Sanitization: None present.
  • Note: Because the skill lacks any dangerous capabilities (shell execution, network requests, etc.), this ingestion point does not pose a significant risk.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 01:08 PM
Security Audit — agent-trust-hub — youtube-ads