skills/aeondave/malskill/rust-testing/Gen Agent Trust Hub

rust-testing

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill recommends the installation of several well-known community tools for the Rust ecosystem, such as cargo-fuzz, cargo-mutants, cargo-nextest, and cargo-afl. These are standard utilities for testing and development.
  • [COMMAND_EXECUTION]: The skill provides a comprehensive list of cargo commands and flags for the agent to execute, including testing, coverage collection, and memory safety analysis with Miri. These commands are within the expected scope of a testing-focused skill.
  • [INDIRECT_PROMPT_INJECTION]: The skill operates on Rust source code and test files, which represents an ingestion surface for untrusted data.
  • Ingestion points: Analyzes and reviews .rs code files as described in SKILL.md.
  • Boundary markers: None explicitly defined in the skill instructions for segregating user-provided code from instructions.
  • Capability inventory: Execution of shell commands via cargo is supported as detailed in references/commands.md.
  • Sanitization: The skill provides guidance on writing safe tests but does not include explicit prompt sanitization instructions for the agent when processing untrusted code.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 09:56 AM
Security Audit — agent-trust-hub — rust-testing