agency-batch-auditor

Pass

Audited by Gen Agent Trust Hub on Jul 16, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [NO_CODE]: The skill consists entirely of markdown instructions and metadata within SKILL.md. It does not include any scripts, executables, or code files.
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface because it is designed to ingest and process content from external URLs.
  • Ingestion points: External URLs provided as batch input in the 'Quick Start' section.
  • Boundary markers: Absent; the instructions do not specify the use of delimiters or 'ignore' instructions for the processed site content.
  • Capability inventory: The skill is a meta-orchestrator that calls other skills (arb-full-audit, ads-readiness-assessment) but does not directly execute system commands or network requests.
  • Sanitization: No input validation or content sanitization is described in the instruction set.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 16, 2026, 01:16 PM
Security Audit — agent-trust-hub — agency-batch-auditor