prepare-commit

Pass

Audited by Gen Agent Trust Hub on Nov 14, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill instructions require the agent to read and summarize external artifacts such as tickets or task descriptions. These sources are considered untrusted data and could contain embedded instructions designed to manipulate the agent's behavior during the commit process.
  • Ingestion points: Project tickets, task descriptions, and other external documentation used as a starting point for the conversation.
  • Boundary markers: There are no defined delimiters or specific instructions provided to the agent to ignore or isolate potentially malicious instructions within the artifacts.
  • Capability inventory: The skill has the capability to execute project-specific shell commands for linting and testing, as well as git operations including staging files and committing changes.
  • Sanitization: The instructions do not specify any sanitization, filtering, or validation steps for the content retrieved from external artifacts.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 14, 2026, 09:21 AM