ads-audit

Pass

Audited by Gen Agent Trust Hub on Apr 5, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill instructions are benign and professional, outlining standard procedures for digital marketing audits without any suspicious command execution or safety bypasses.
  • [PROMPT_INJECTION]: The skill processes untrusted external data from advertising platforms, creating a surface for potential indirect prompt injection.
  • Ingestion points: Analyzes advertising account exports, campaign history, and screenshots provided by the user (SKILL.md).
  • Boundary markers: The audit process does not specify the use of delimiters or instructions for the agent to ignore content embedded within the reports.
  • Capability inventory: The skill is limited to data analysis, scoring, and generating markdown reports; no system-level commands or network exfiltration patterns are present in the analyzed file.
  • Sanitization: No validation or sanitization routines are mentioned for the external advertising data.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 5, 2026, 06:42 PM
Security Audit — agent-trust-hub — ads-audit