skills/guillevc/skills/2-commit-fast/Gen Agent Trust Hub

2-commit-fast

Warn

Audited by Gen Agent Trust Hub on Apr 9, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill mandates the execution of shell commands (git commit) while explicitly instructing the agent to bypass human review. It contains directions such as 'No confirmation step — speed is the point' and 'Do not ask the user to confirm the message — just commit', which suppresses standard safety protocols for autonomous write operations.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by analyzing data from potentially untrusted sources.
  • Ingestion points: The skill reads the output of git diff --cached, git log, and git branch --show-current (SKILL.md, Step 2).
  • Boundary markers: There are no delimiters or markers used to separate the analyzed git data from the agent's core instructions.
  • Capability inventory: The agent has the capability to perform repository writes via the git commit command (SKILL.md, Step 5).
  • Sanitization: There is no logic to sanitize or validate the content of the diffs or branch names to prevent malicious instructions from influencing the agent's behavior.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 9, 2026, 12:34 AM
Security Audit — agent-trust-hub — 2-commit-fast