pi-agent-rust

Pass

Audited by Gen Agent Trust Hub on Apr 10, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill focuses on standard software development tasks such as compilation, linting, and unit testing within a local Rust repository environment.- [COMMAND_EXECUTION]: The instructions direct the agent to execute project-specific shell commands and scripts. These include Rust development tools like cargo check, cargo clippy, and cargo fmt, as well as project-local scripts like tests/installer_regression.sh and scripts/skill-smoke.sh.- [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it processes project files and maintains the ability to execute shell commands. \n
  • Ingestion points: Reads repository contents including source code (src/**) and scripts (install.sh, uninstall.sh). \n
  • Boundary markers: None explicitly defined to isolate project data from the instruction context. \n
  • Capability inventory: Executes subprocesses via bash, cargo, and the rch wrapper. \n
  • Sanitization: No explicit sanitization or validation of the ingested repository content is mentioned.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 10, 2026, 08:14 AM
Security Audit — agent-trust-hub — pi-agent-rust