arb-full-audit

Pass

Audited by Gen Agent Trust Hub on Jul 16, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: Indirect Prompt Injection Surface. The skill's core functionality involves fetching and analyzing content from a user-provided url. This creates an attack surface where instructions embedded in the target website could attempt to override the auditor's logic or bias the scoring process.
  • Ingestion points: The url parameter in SKILL.md serves as the entry point for untrusted external data.
  • Boundary markers: There are no explicit instructions or delimiters defined to isolate the external content from the agent's instructions.
  • Capability inventory: The orchestrator invokes multiple sub-skills (technical-audit, content-audit, policy-risk-scanner, etc.) and generates a final report and scorecard.
  • Sanitization: The instructions do not mention any sanitization, filtering, or validation of the content retrieved from the external URL.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 16, 2026, 01:16 PM
Security Audit — agent-trust-hub — arb-full-audit