seo-ai-crawlers
Pass
Audited by Gen Agent Trust Hub on Sep 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes untrusted data from external web sources to audit AI crawler access and citability.
- Ingestion points: The skill reads site-specific configuration files such as
robots.txtandllms.txt, as well as raw and rendered HTML (raw_html,rendered_dom) from target websites. - Boundary markers: The instructions do not define specific delimiters or boundary markers to isolate external content from the agent's instructions.
- Capability inventory: The skill possesses capabilities including
Bash(executing a local Node.js script),WebFetch(network requests to fetch target site data), andRead(accessing local files and references). - Sanitization: There is no evidence of explicit sanitization or filtering of the content fetched from external websites before it is processed by the agent.
- [COMMAND_EXECUTION]: The skill executes a local Node.js script to parse robots.txt and sitemap data.
- Evidence: The verification section specifies the execution of
node ${CLAUDE_SKILL_DIR}/../../scripts/parse-robots-sitemap.mjs --url <u>to resolve directives for AI user-agents. This script is located within the agent's local environment.
Audit Metadata