subagent-delegation

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill facilitates the analysis of external codebase files, which creates a surface for indirect prompt injection if those files contain malicious instructions or hidden commands.
  • Ingestion points: Examples in references/patterns.md (Pattern 3: File Analysis) and examples/delegation-patterns-examples.md (Example 3: Code Analysis) demonstrate subagents reading and summarizing files and patterns directly from the project directory.
  • Boundary markers: SKILL.md defines a manual review process and Quality Control checklist, but the provided prompt templates do not utilize technical delimiters (like XML tags or clear separators) to isolate processed content from instructions.
  • Capability inventory: The skill uses the runSubagent and mcp_sequentialthi_sequentialthinking tools to perform analysis and task execution.
  • Sanitization: There is no evidence of sanitization, escaping, or filtering applied to the content of the files before they are interpolated into the subagent's prompt context.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 12:41 AM