git-commit

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local shell scripts and git commands to gather repository context and perform commits.
  • Evidence: Execution of bash /mnt/skills/user/git-commit/scripts/generate-commit-msg.sh and git commit.
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection (Category 8) because it ingests untrusted data from the git repository that could contain malicious instructions.
  • Ingestion points: Untrusted data enters the agent context through staged_diff and recent_commits gathered in scripts/generate-commit-msg.sh.
  • Boundary markers: The skill lacks explicit boundary markers or instructions to ignore embedded commands within the diff data during analysis.
  • Capability inventory: The skill has the capability to execute shell scripts (generate-commit-msg.sh) and perform file system modifications via git commit.
  • Sanitization: There is no evidence of sanitization or filtering of the staged_diff content before it is processed by the LLM for message generation.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 11:46 AM