asa-negative-keywords

Pass

Audited by Gen Agent Trust Hub on Aug 22, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill instructions are focused on legitimate Apple Search Ads optimization and do not contain any obfuscated code, unauthorized data access, or persistence mechanisms.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests search term data originating from external API reports, which could potentially contain adversarial instructions aimed at influencing agent behavior.
  • Ingestion points: Search term strings retrieved via the asa_report_search_terms tool (SKILL.md).
  • Boundary markers: Absent; the instructions do not specify the use of delimiters or 'ignore' instructions for the search term data.
  • Capability inventory: The skill has the ability to modify advertising account configurations using the asa_create_campaign_negative_keywords and asa_create_adgroup_negative_keywords tools (SKILL.md).
  • Sanitization: Absent; the skill classifies and processes search terms without explicit validation or filtering logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 22, 2026, 10:19 PM
Security Audit — agent-trust-hub — asa-negative-keywords