ai-search-visibility-audit
Pass
Audited by Gen Agent Trust Hub on Aug 28, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches robots.txt and public website content from user-provided domains to perform visibility checks. These operations are restricted to public data and are a primary requirement of the skill's auditing function.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests content from external websites which could theoretically contain instructions intended to influence agent behavior. However, the skill provides specific analysis criteria that guide the agent to evaluate the data purely for SEO and retrieval purposes.
- Ingestion points: robots.txt files and three user-selected web pages (SKILL.md).
- Boundary markers: Absent.
- Capability inventory: The agent is limited to web searching, fetching public URL content, and generating reports. It does not request file system writes, credential access, or sensitive network operations.
- Sanitization: Not specified, though the audit is focused on specific structural properties (e.g., headings, structured data).
Audit Metadata