meta-ads-analyzer

Pass

Audited by Gen Agent Trust Hub on Feb 27, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill is designed to ingest and process external data, making it susceptible to indirect prompt injection if malicious instructions are embedded in the analyzed content.
  • Ingestion points: User-provided CSV exports, screenshots, and raw data from Meta Ads Manager (referenced in SKILL.md).
  • Boundary markers: None. The skill lacks instructions to use delimiters or 'ignore' commands within the analyzed data.
  • Capability inventory: Mentions interaction with a 'get_recommendations' API and the generation of optimization recommendations.
  • Sanitization: No sanitization or validation of the input data is described in the skill instructions.
  • [NO_CODE]: The skill consists entirely of markdown documentation and instructional text. No executable scripts, Python packages, or Node.js dependencies are included.
  • [SAFE]: No hardcoded credentials, sensitive file paths, or unauthorized network operations were detected. The instructions provided are consistent with the stated purpose of Meta Ads performance analysis.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 27, 2026, 08:46 AM