multi-ticket-workflow
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists of high-level procedural instructions for coordinating agent tasks. It does not include shell commands, remote scripts, or sensitive file access patterns.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it is designed to ingest and act upon untrusted external data. * Ingestion points: The workflow instructions in SKILL.md require the agent to 'Read every ticket the user named' and 'dispatch one read-only code mapping pass per affected ticket', which pulls in external user-controlled content and codebase data. * Boundary markers: The skill does not define specific delimiters or instructions to ignore potential commands embedded within the ticket requirements. * Capability inventory: The skill is authorized to delegate tasks to sub-agents (architecture-code-auditor, implementation-coordinator), generate implementation plans, and write durable orchestration notes to the local scratch space. * Sanitization: There is no evidence of sanitization or filtering of external ticket content before it is processed for planning and delegation.
Audit Metadata