sprint
Pass
Audited by Gen Agent Trust Hub on Mar 29, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
Bashtool to execute thegit checkout -bcommand. This is used to create local development branches based on ticket titles provided by the user, which is the primary intended functionality of the skill.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external ticket management systems like Jira, Linear, or GitHub. This data is untrusted and could contain malicious instructions. However, the risk is mitigated by the skill's instructions for the agent to transform the input into a highly constrained format (kebab-case, maximum 40 characters) before using it in a shell command.\n - Ingestion points: Ticket title and description provided during the trigger phase (from SKILL.md).\n
- Boundary markers: Absent; the skill does not define specific delimiters for the external content.\n
- Capability inventory: Access to the
Bashtool for local command execution.\n - Sanitization: The skill enforces output constraints—specifically kebab-case formatting and length limits—which serve as a sanitization mechanism to prevent command injection.
Audit Metadata