parallel-execution
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFENO_CODE
Full Analysis
- Category 8: Indirect Prompt Injection (SAFE): The skill outlines patterns for spawning subagents with dynamic prompts. While this identifies a structural surface for indirect injection via project context, the skill itself is instructional documentation and does not contain malicious code or payloads.
- Ingestion points: Subagent prompts are constructed using codebase context and task descriptions as shown in SKILL.md.
- Boundary markers: Templates provided in the instructions do not include specific delimiters or ignore-instructions for untrusted content.
- Capability inventory: The patterns utilize the 'Task' and 'TaskOutput' tools to perform parallel operations.
- Sanitization: Not applicable to this pattern library.
Audit Metadata