seo
Pass
Audited by Gen Agent Trust Hub on Aug 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection through the ingestion of external URL content.
- Ingestion points: Commands such as /seo audit and /seo page take user-supplied URLs as input.
- Boundary markers: No specific delimiters or safety instructions are defined in the skill instructions to separate external data from agent commands.
- Capability inventory: The skill is allowed to use Bash, WebFetch, and file system tools (Read, Grep, Glob).
- Sanitization: The instructions do not describe any mechanisms for validating or sanitizing the content fetched from target websites.
- [COMMAND_EXECUTION]: The skill uses the Bash tool to perform technical audits. Reference files provide examples of executing shell commands like curl and npx lighthouse for data collection.
- [EXTERNAL_DOWNLOADS]: The skill involves downloading and executing tools from external registries. Specifically, references/cwv-thresholds.md mentions using npx to run lighthouse from the npm registry. This is documented as a standard operation for SEO analysis utilizing well-known services.
Audit Metadata