ads-batch

Pass

Audited by Gen Agent Trust Hub on May 18, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local Python script python .claude/skills/ads/validate.py to validate generated ad content. This command runs against the output file created by the skill within the project environment.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user data (keywords, landing pages, and USPs) provided via files or inline text. While this constitutes an attack surface, the risk is inherent to the skill's primary purpose of content generation.
  • Ingestion points: Ad group data provided by the user in CSV or text format.
  • Boundary markers: None explicitly defined for delimiting user input during processing.
  • Capability inventory: File system read/write access and the ability to execute a local Python script via Bash.
  • Sanitization: No explicit sanitization or filtering of input content is described in the prompt.
Audit Metadata
Risk Level
SAFE
Analyzed
May 18, 2026, 08:28 AM
Security Audit — agent-trust-hub — ads-batch