asa-weekly-optimization

Pass

Audited by Gen Agent Trust Hub on Aug 22, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface through the processing of search term reports which are then used to influence campaign targeting.
  • Ingestion points: The asa_report_search_terms tool retrieves user-generated search query data from the Apple App Store, introducing external, untrusted content into the agent context.
  • Boundary markers: The instructions do not include delimiters or specific guidance to ensure the agent ignores potentially malicious instructions embedded within the search term data.
  • Capability inventory: The agent has write access to the Apple Search Ads account via asa_update_targeting_keywords and asa_create_targeting_keywords, which are used to act upon the ingested search term data.
  • Sanitization: There are no described validation or filtering steps for search terms before they are processed by the agent to make bid and keyword changes.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 22, 2026, 10:19 PM
Security Audit — agent-trust-hub — asa-weekly-optimization