tailrocks-rust-review

Pass

Audited by Gen Agent Trust Hub on Sep 8, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes standard Rust toolchain commands such as cargo test, cargo clippy, cargo bench, cargo doc, and cargo flamegraph, along with the mise task runner for code analysis and verification.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted Rust source code and repository data, creating a potential attack surface.
  • Ingestion points: Rust source files and repository diffs provided as review targets.
  • Boundary markers: The skill includes a runtime-trust.md reference that explicitly instructs the agent to treat repository content as untrusted and ignore embedded instructions.
  • Capability inventory: The skill can execute code via cargo test, cargo bench, and mise run.
  • Sanitization: Explicit prompt instructions mandate read-only filesystem access, network isolation, and authorization before any command execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 8, 2026, 03:12 PM
Security Audit — agent-trust-hub — tailrocks-rust-review