handle-tickets
Pass
Audited by Gen Agent Trust Hub on Aug 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The orchestrator manages local worktrees and executes Git operations, including committing and pushing code to remote branches.
- [PROMPT_INJECTION]: The skill defines a multi-agent hierarchy using specific footers that instruct sub-agents to disregard interactive user input and return targeted blockers only to their parent agent.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its core function of reading and acting upon data from external ticket trackers and PR comments.
- Ingestion points: Reads ticket bodies and PR comments during the 'Gather Context' and 'PR Review Activation' phases.
- Boundary markers: Uses structured footer templates and atomic review packets to delimit information exchange between roles.
- Capability inventory: Includes spawning sub-agents, writing files, and performing Git operations (commit, push, merge).
- Sanitization: Mandates that workers redact sensitive information from implementation-relevant facts in their handoff packets.
Audit Metadata