absolute-simplify
Pass
Audited by Gen Agent Trust Hub on Jul 8, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or persistence mechanisms were detected. The skill maintains a clear focus on code simplification and uses local context appropriately.\n- [EXTERNAL_DOWNLOADS]: The README.md specifies an installation method via 'npx' from the author's repository, which is a standard procedure for this platform.\n- [COMMAND_EXECUTION]: The skill executes local 'git' commands to identify changes and project-defined test/lint runners (e.g., 'npm test', 'pytest', 'go test') to verify refactors. These operations are limited to the local repository context and are within the expected behavior for a code refactoring tool.\n- [PROMPT_INJECTION]: The skill processes untrusted project files which presents a surface for indirect prompt injection.\n
- Ingestion points: Reads staged/unstaged source code and project configuration files (SKILL.md, Phase 1 & 2).\n
- Boundary markers: Absent; the instructions do not explicitly delimit untrusted code content with protective instructions.\n
- Capability inventory: Includes file system writes (SKILL.md, Phase 5) and shell execution of project-defined scripts (SKILL.md, Phase 6).\n
- Sanitization: No specific sanitization or filtering of code comments is performed.\n
- Note: The risk is significantly mitigated by 'Hard Gates' (SKILL.md) that strictly prohibit changes to observable behavior and ensure project standards are followed.
Audit Metadata