pagespeed-insights
Pass
Audited by Gen Agent Trust Hub on Mar 10, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of instructional markdown and code examples for reference. It does not perform any system actions, network requests, or file modifications.
- [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow for analyzing external web pages, which are untrusted data sources. Ingestion points: Web content audited by the agent as described in SKILL.md. Boundary markers: None provided in the instructions to delimit the web content from the agent's instructions. Capability inventory: No scripts or system capabilities are implemented in this skill. Sanitization: No sanitization or validation logic is defined within the skill. The security of this operation depends on the host environment's handling of untrusted data.
Audit Metadata