doc-refactor

Pass

Audited by Gen Agent Trust Hub on Apr 20, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill possesses a standard attack surface for indirect prompt injection as it processes external document content.
  • Ingestion points: The skill reads file content based on the path provided in $ARGUMENTS through the subagent prompt and Read tool.
  • Boundary markers: The prompt instructions for the subagent do not define clear delimiters or 'ignore embedded instructions' warnings for the document content.
  • Capability inventory: The agent has access to file system tools (Read, Grep, Glob, Edit) and can dispatch tasks to other agents.
  • Sanitization: There is no evidence of content validation or sanitization before the document data is incorporated into the agent context for refactoring.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 20, 2026, 07:24 PM