ads-youtube
Pass
Audited by Gen Agent Trust Hub on Feb 26, 2026
Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill is composed of Markdown instructions and YAML configuration without any Python, Node.js, or Shell scripts.
- [SAFE]: The skill's process steps involve reading local reference files (e.g.,
../ads/references/benchmarks.md), which is standard behavior for modular agent skills. - [PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection via the processing of external YouTube Ads data exports. 1. Ingestion points: YouTube Ads data (Google Ads export) referenced in SKILL.md. 2. Boundary markers: Absent; no specific delimiters or instruction-ignore warnings are defined. 3. Capability inventory: Limited to reading local documentation and generating text reports; no network, file-write, or command execution capabilities were detected. 4. Sanitization: Absent; the instructions do not describe validation or sanitization of input data. This surface is assessed as safe due to the absence of exploitable tools.
Audit Metadata