troubleshoot-website
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill has the surface area for indirect prompt injection as it processes data from external websites and logs that could contain malicious instructions designed to influence the agent.
- Ingestion points: Untrusted data is ingested via website content retrieval (
hosting_files_website-content), runtime logs (hosting_nodejs_runtime-logs), and build logs (hosting_nodejs_build-logs) as described in SKILL.md. - Boundary markers: While explicit boundary markers for data are not defined in the skill instructions, the agent is instructed to analyze data read-only first.
- Capability inventory: The skill possesses the ability to modify website configurations, toggle SSL settings, change PHP options, and deactivate WordPress plugins through the Hostinger MCP (SKILL.md).
- Sanitization: The skill mitigates risks by enforcing a human-in-the-loop policy, requiring the agent to 'Stay read-only until the cause is stated and the user agrees to the fix' before performing any write operations.
Audit Metadata