polish
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists entirely of natural language instructions and a checklist. It does not contain any executable scripts, shell commands, or external package dependencies. All external links point to well-known developer resource sites and blogs.
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to analyze and modify existing codebases based on a checklist. This establishes a surface for indirect prompt injection where an attacker could place malicious instructions inside the files being polished (e.g., in HTML comments or text content).
- Ingestion points: The agent reads project files (HTML, CSS, JS) to evaluate them against the checklist.
- Boundary markers: None present in the skill file to delimit user-provided content from instructions.
- Capability inventory: The skill itself contains no commands or network operations; it relies on the agent's native file-system capabilities.
- Sanitization: No explicit sanitization or filtering logic is provided within the checklist.
Audit Metadata