ads-competitor

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • Indirect Prompt Injection (LOW): Potential surface for indirect prompt injection through the processing of external advertising data.\n
  • Ingestion points: Public ad libraries (Meta, Google, TikTok, LinkedIn) and user-provided auction insights from the browser/account.\n
  • Boundary markers: The skill lacks explicit delimiters or instructions to ignore embedded commands in the ad copy it researches.\n
  • Capability inventory: The skill is designed to generate markdown reports (e.g., COMPETITOR-INTELLIGENCE-REPORT.md) based on findings.\n
  • Sanitization: No sanitization of external text is defined in the instruction set.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:35 PM