commit-message-generator

Pass

Audited by Gen Agent Trust Hub on May 19, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill is designed to execute several 'dxs' CLI commands (e.g., 'dxs source branch show', 'dxs -b source changes') to gather metadata and code diffs. It passes a user-supplied branch ID directly into these shell commands, which could be exploited for command injection if the input is not properly sanitized by the underlying execution platform.
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it analyzes untrusted content from feature branch diffs to generate summaries.
  • Ingestion points: Phase 2 (Gather) fetches raw configuration changes and code diffs using 'dxs -b source changes --with-diffs'.
  • Boundary markers: The workflow lacks explicit delimiters or instructions to the model to ignore any embedded commands within the fetched diffs.
  • Capability inventory: The skill produces text meant for commits and can write data to a permanent Knowledge Base via 'CreateKnowledgeNode'.
  • Sanitization: No sanitization or validation of the branch content is mentioned before the data is passed to the analysis phase.
Audit Metadata
Risk Level
SAFE
Analyzed
May 19, 2026, 07:36 PM
Security Audit — agent-trust-hub — commit-message-generator