ads-audit

Pass

Audited by Gen Agent Trust Hub on Feb 28, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: No malicious patterns detected. The skill's behavior aligns with its stated purpose of auditing advertising accounts.
  • [NO_CODE]: The skill consists of markdown instructions and does not include any executable code or scripts.
  • [PROMPT_INJECTION]: The skill has an indirect prompt injection surface (Category 8) because it processes untrusted external data such as advertising exports and search reports. Mandatory Evidence Chain: 1. Ingestion points: account exports and search term reports described in SKILL.md. 2. Boundary markers: Absent. 3. Capability inventory: The skill generates markdown reports and delegates to subagents. 4. Sanitization: Absent. The risk is considered low as the skill's capabilities are limited to generating reports within the agent's context.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 28, 2026, 03:39 AM