ads-audit

Pass

Audited by Gen Agent Trust Hub on Apr 20, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: The skill is entirely declarative and consists of markdown-based instructions for data analysis. No scripts or executable files are included in the package.
  • [NO_CODE]: No external software dependencies, package installations, or remote script downloads were detected.
  • [DATA_EXFILTRATION]: There is no evidence of network activity or attempts to transmit data to external domains.
  • [PROMPT_INJECTION]: The skill defines an attack surface for indirect prompt injection as it processes user-provided screenshots and CSV exports (SKILL.md, Step 1). However, the risk is negligible as the skill lacks sensitive capabilities. Ingestion points: Ad data/metrics in SKILL.md. Boundary markers: Absent. Capability inventory: No tools or subprocesses used. Sanitization: Absent.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 20, 2026, 01:43 AM