seo-visibility-expert
Pass
Audited by Gen Agent Trust Hub on Mar 5, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted data from external websites.\n
- Ingestion points: Uses WebFetch and WebSearch to retrieve live web content for SEO audits.\n
- Boundary markers: No delimiters are used to separate fetched content from system instructions.\n
- Capability inventory: Accessible tools include Bash, Write, Edit, and Read, allowing for significant system impact.\n
- Sanitization: Fetched content is not sanitized or validated before processing.\n- [COMMAND_EXECUTION]: The skill is authorized to use Bash and file system tools. These high-privilege capabilities are intended for technical audits but could be leveraged maliciously if the agent's behavior is overridden by external content.
Audit Metadata