paid-ads

Pass

Audited by Gen Agent Trust Hub on Nov 17, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from ad platform exports and matrix files which could contain malicious instructions.
  • Ingestion points: Reads './campaigns//ad-matrix.json' and processes pasted platform exports (CSV/screenshots) in Results Review mode.
  • Boundary markers: The instructions do not define delimiters or specific 'ignore' markers for untrusted content.
  • Capability inventory: The skill can write files to the 'assets' directory, perform network mutations via the Meta and Google Ads APIs, and execute local scripts.
  • Sanitization: No sanitization or validation of the ingested external data is performed before it is used by the agent.
  • [DYNAMIC_EXECUTION]: The skill executes local Python scripts using computed paths (e.g., brand_context.py), which is a dynamic loading pattern.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 17, 2026, 04:24 PM