ads-audit

Pass

Audited by Gen Agent Trust Hub on May 5, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [NO_CODE]: The skill package contains only a Markdown file (SKILL.md) with configuration metadata and human-readable instructions. No executable scripts, binaries, or active code components are present.
  • [INDIRECT_PROMPT_INJECTION]: The skill instructions define a process for ingesting untrusted external data, which creates a theoretical attack surface for indirect prompt injection.
  • Ingestion points: User-provided ad platform exports (CSV/reports), API data, and screenshots defined in the 'Data Collection' section of SKILL.md.
  • Boundary markers: No delimiters or explicit instructions to ignore embedded commands are specified in the process.
  • Capability inventory: The skill is designed to generate multiple report files including 'ADS-AUDIT-REPORT.md' and 'ADS-ACTION-PLAN.md'.
  • Sanitization: No sanitization or data validation steps for the content of the exports are mentioned in the instructions.
  • [SAFE]: The behavioral patterns described in the skill (collecting exports, calculating scores, and generating reports) align perfectly with the described purpose of a multi-platform advertising audit. No malicious patterns such as exfiltration, persistence, or obfuscation were detected.
Audit Metadata
Risk Level
SAFE
Analyzed
May 5, 2026, 10:42 AM
Security Audit — agent-trust-hub — ads-audit