pseudo-elements
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides instructional rules for code review. It does not perform network operations, access sensitive credentials, or attempt to persist on the host system. The logic is entirely based on pattern matching within CSS and JavaScript files for architectural best practices.
- [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it is designed to ingest and analyze external source code. 1. Ingestion points: Processes code from files specified by the user or identified via search patterns (SKILL.md). 2. Boundary markers: None are defined to separate the instructions from the code being analyzed. 3. Capability inventory: The skill does not use any capabilities for network requests, file writing, or shell command execution. 4. Sanitization: No specific sanitization or filtering of the input code is described. This surface is considered safe due to the complete absence of dangerous side-effect capabilities.
Audit Metadata