Skills
Navigate
skills/code-yeongyu/oh-my-openagent/git-master/Gen Agent Trust Hub

git-master

Pass

Audited by Gen Agent Trust Hub on Sep 19, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes repository history which could include untrusted content designed to influence agent logic.\n
  • Ingestion points: Reads repository history and state using git log, git diff, and git show as described in SKILL.md.\n
  • Boundary markers: Uses a Mode Gate to classify user intent and a series of Safety Checks to ensure the repository state is known before execution in SKILL.md.\n
  • Capability inventory: Possesses the ability to execute shell-based git commands that modify the repository history and structure in SKILL.md.\n
  • Sanitization: Requires verification of diffs and log outputs after operations, and resolution of conflicts based on intent rather than blind acceptance in SKILL.md.\n- [COMMAND_EXECUTION]: The skill's primary functionality is delivered through the execution of Git command-line tools.\n
  • Evidence: Multiple instances of git commands (e.g., git status, git log, git rebase) are used to gather data and perform operations in SKILL.md.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 19, 2026, 06:00 PM