skills/tokenrollai/cc-plugin/commit/Gen Agent Trust Hub

commit

Fail

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: HIGHCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION] (HIGH): The skill executes git commit -m "<message>" via the Bash tool using AI-generated content. This creates a command injection vulnerability if the message contains shell metacharacters like backticks or subshells, as the content is not escaped before being passed to the shell.
  • [PROMPT_INJECTION] (LOW): The skill lacks defenses against indirect prompt injection. 1. Ingestion points: Data is pulled from git log and git diff (SKILL.md). 2. Boundary markers: None. 3. Capability inventory: Use of the Bash tool for local command execution. 4. Sanitization: None. The AI-generated output is used directly in a shell command without validation.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 17, 2026, 06:50 PM