agent-search-optimisation

Pass

Audited by Gen Agent Trust Hub on Jul 24, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses a local script scripts/audit-agent-readiness.mjs to automate the technical audit process. This script is used to identify common machine-readable files and metadata.
  • [EXTERNAL_DOWNLOADS]: The skill performs network requests to user-provided URLs to retrieve public assets such as robots.txt, sitemap.xml, and llms.txt. These operations are transparently documented as part of the audit workflow.
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface because it processes content from external websites. While malicious instructions could be embedded in the audited site's metadata or orientation files (like llms.txt), this is an inherent risk of any web-auditing or browsing tool and is mitigated by the structured JSON output of the audit script.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 24, 2026, 12:21 AM
Security Audit — agent-trust-hub — agent-search-optimisation