make-release

Pass

Audited by Gen Agent Trust Hub on Feb 28, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [SAFE]: The skill's instructions are consistent with its stated goal of preparing a software release. No malicious patterns or security risks were identified.
  • [COMMAND_EXECUTION]: The skill executes standard CLI commands, including Git operations and poetry build. These are routine tasks in a developer workflow and are used appropriately within the context of the skill.
  • [PROMPT_INJECTION]: The instructions contain no attempts to bypass safety filters, manipulate the model's system prompt, or override core safety guidelines.
  • [DATA_EXFILTRATION]: The skill does not access sensitive credentials or communicate with external network endpoints, minimizing the risk of data exfiltration.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 28, 2026, 09:35 AM