code-tidy
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION] (LOW): The skill executes shell commands including cd, git, and awk. The use of the ${PROJECT_DIR} variable in shell interpolation presents a potential command injection surface if the directory path provided to the agent is maliciously crafted.
- [PROMPT_INJECTION] (LOW): The skill is susceptible to indirect prompt injection. 1. Ingestion points: Reads local Java source code files and Git status output. 2. Boundary markers: None. 3. Capability inventory: Local file read/write access and shell command execution. 4. Sanitization: None. Malicious instructions embedded within Java comments in processed files could theoretically influence the agent's logic during the formatting process.
Audit Metadata