oxidizer-workflow

Pass

Audited by Gen Agent Trust Hub on Nov 2, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes a custom recipe runner amplihack and various standard Rust development tools including cargo init, cargo clippy, cargo fmt, cargo test, cargo-udeps, cargo-deny, and cargo bench. These tools are used to scaffold projects, run tests, and perform static analysis on the generated Rust code.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process Python codebases, which represents a potential attack surface for indirect prompt injection. Ingestion points: The python_package_path (SKILL.md) specifies the source code to be migrated. Boundary markers: The instructions do not define specific delimiters or warnings to ignore instructions embedded within the source Python code. Capability inventory: The workflow involves file system modifications, dependency resolution, and execution of code through test and benchmark suites. Sanitization: There is no mention of sanitizing or filtering the source code content before it is processed by the agent's migration logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 2, 2026, 04:52 PM