skills/leynos/rust-skill/kani/Gen Agent Trust Hub

kani

Pass

Audited by Gen Agent Trust Hub on Nov 10, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill documentation and Makefile reference the 'prover-tools' utility, which is fetched from the author's GitHub repository (leynos/rust-prover-tools).
  • [REMOTE_CODE_EXECUTION]: The Makefile uses 'uv tool run' to execute the 'prover-tools' CLI directly from a remote Git repository source, which is pinned to a specific commit for integrity.
  • [COMMAND_EXECUTION]: The skill facilitates the installation of the 'kani-verifier' tool via 'cargo install' and manages verification runs using 'cargo kani' within the user's workspace.
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it is designed to process and maintain Rust source code and verification harnesses.
  • Ingestion points: Rust source code and Kani harness files in the repository.
  • Boundary markers: Absent.
  • Capability inventory: Orchestration of 'cargo install', 'cargo kani', and 'uv tool run'.
  • Sanitization: Absent; the skill interacts directly with code stored in the environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 10, 2026, 09:59 PM