seo-ai-crawlers

Pass

Audited by Gen Agent Trust Hub on Jun 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local utility script parse-robots-sitemap.mjs using Node.js to verify robots.txt configurations. This script is part of the vendor's provided repository structure and is used for verification purposes.
  • [PROMPT_INJECTION]: The skill processes untrusted external data from audited web pages and robots.txt files, which constitutes an indirect prompt injection surface. Maliciously crafted content in these external sources could attempt to influence the agent's reasoning.
  • Ingestion points: Raw HTML (raw_html), rendered DOM (rendered_dom), and site robots.txt files.
  • Boundary markers: None identified. The skill does not specify the use of delimiters or warnings to ignore instructions embedded in the crawled content.
  • Capability inventory: Access to Bash (executing local scripts) and WebFetch (network retrieval).
  • Sanitization: No specific content sanitization or validation steps are described for the external data before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 15, 2026, 08:09 PM
Security Audit — agent-trust-hub — seo-ai-crawlers