ce-simplify-code
Pass
Audited by Gen Agent Trust Hub on Jun 23, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local development commands to facilitate code analysis and verification. Specifically, it uses
git diffto identify modified code and invokes user-configured project tools such aseslint,knip,ruff,tsc,golangci-lint, andast-grepfor linting and dead-code detection. It also executes the project's test suite to ensure functional parity after refactoring. - [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it ingests and processes untrusted code changes from the filesystem. Instructions embedded in code comments within the analyzed files could potentially influence the behavior of the sub-reviewers.
- Ingestion points: Code changes extracted via
git diffor direct file reads in SKILL.md Step 1. - Boundary markers: Absent; the skill does not explicitly use delimiters or instruction-ignore headers when passing code to sub-agents.
- Capability inventory: File writing (applying fixes), shell command execution (git, linters, tests), and sub-agent spawning.
- Sanitization: Not present; the skill treats the codebase content as plain text for analysis.
Audit Metadata