security-vite
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes external content from local project files, which could potentially contain malicious instructions intended to influence the agent's behavior during a security audit.\n
- Ingestion points: Reads project files including
.env,vite.config.ts, and bundle files in thedist/directory.\n - Boundary markers: No explicit instructions or delimiters are used to warn the agent to ignore instructions embedded in the analyzed data.\n
- Capability inventory: The agent utilizes file search and pattern matching tools (
grep,rg,find,fd) to process the contents of these files.\n - Sanitization: The skill does not implement validation or escaping of the file contents before they are presented to the agent.
Audit Metadata