geo-technical
Pass
Audited by Gen Agent Trust Hub on Mar 27, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to use shell commands like
curlto fetch robots.txt, sitemaps, and raw HTML content for analysis and performance timing. - [EXTERNAL_DOWNLOADS]: The skill fetches resources from remote domains to evaluate SEO metrics such as indexability and crawlability.
- [PROMPT_INJECTION]: The skill processes untrusted data from external websites, which creates a potential surface for indirect prompt injection attacks where malicious instructions could be embedded in metadata or content.
- Ingestion points: External content is fetched from target URLs, robots.txt, and XML sitemaps using
curlorWebFetch(SKILL.md). - Boundary markers: The instructions do not provide explicit delimiters or warnings to ignore instructions embedded within the fetched content.
- Capability inventory: The agent can execute shell commands (
curl) and write detailed analysis reports to the file system. - Sanitization: No sanitization or validation of the external content is described before it is parsed and analyzed.
Audit Metadata