skills/gooseworks-ai/goose-skills/improve-search-visibility-page-and-foundation-check/Gen Agent Trust Hub
improve-search-visibility-page-and-foundation-check
Pass
Audited by Gen Agent Trust Hub on Nov 8, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to use a shell to perform network requests, specifically simulating bot user-agents (OAI-SearchBot, PerplexityBot) to test CDN blocking behavior.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external websites as part of its core auditing function, which creates a surface for instructions embedded in those sites to influence the agent.
- Ingestion points: Audited website pages, robots.txt files, and XML sitemaps are fetched and processed in
SKILL.mdusinggooseworks:knowledge_searchand shell commands. - Boundary markers: The instructions do not define explicit delimiters or warnings to the agent to ignore instructions found within the audited content.
- Capability inventory: The skill has shell execution capabilities (for network testing) and writes audit reports/notes to the local filesystem as defined in
SKILL.md. - Sanitization: No specific sanitization, validation, or escaping of the ingested website content is mentioned before it is processed by the agent.
Audit Metadata