seo-unlighthouse
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides instructions for a standard SEO audit workflow using the Unlighthouse tool. It includes safety-oriented instructions that direct the agent to verify installation commands from first-party documentation and obtain explicit user approval before performing network-intensive crawls or package installations.
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the interpretation of external site audit data, which acts as an ingestion point for untrusted information. However, the risk is mitigated by the workflow's requirement for human oversight on sensitive actions.
- Ingestion points: External site audit data from Unlighthouse reports (SKILL.md).
- Boundary markers: None specified.
- Capability inventory: Shell command execution and package installation (SKILL.md).
- Sanitization: Instructions mandate manual verification of commands and user approval for installations.
Audit Metadata