ad-copy-generator

Pass

Audited by Gen Agent Trust Hub on Feb 19, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [NO_CODE] (SAFE): The skill consists entirely of markdown documentation and prompts. There are no scripts (Python, Node.js, Bash) or binary files included.
  • [DATA_EXPOSURE] (SAFE): No sensitive file paths, environment variable access, or hardcoded credential patterns were detected.
  • [EXTERNAL_DOWNLOADS] (SAFE): No external URLs, remote script execution patterns, or package manager installations (pip, npm) were found.
  • [PROMPT_INJECTION] (SAFE): The instructions are focused on ad copy generation and do not contain patterns typical of jailbreaks or safety filter bypasses.
  • [INDIRECT_PROMPT_INJECTION] (LOW): The skill has an ingestion surface for user-provided data. 1. Ingestion points: [product], [audience], and [topic] placeholders in SKILL.md. 2. Boundary markers: Absent. 3. Capability inventory: None (no executable code provided). 4. Sanitization: Absent. The risk is minimal as the skill lacks exploitable capabilities.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 19, 2026, 03:51 PM