lov-optimize-tauri-backend
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted local project files, which creates a potential surface for indirect prompt injection where malicious content in a repository could influence the agent's behavior.\n
- Ingestion points: The skill reads local project files including Rust source code (e.g.,
src-tauri/src/lib.rs),package.json, and project-specific instructions such asAGENTS.mdandCLAUDE.md.\n - Boundary markers: No explicit delimiters or safety instructions are defined to help the agent distinguish between the skill's own instructions and potentially malicious content within the files it analyzes.\n
- Capability inventory: The agent is instructed to write to the file system (refactoring code) and execute potentially high-risk shell commands including
cargo check,cargo fmt, andpnpm exec tsc.\n - Sanitization: The skill does not specify any requirements for the agent to sanitize, filter, or validate the content of the project files before processing them or running associated build and linting tools.
Audit Metadata