docs-maker
Pass
Audited by Gen Agent Trust Hub on Mar 5, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill has a potential surface for indirect prompt injection due to its document processing workflow.
- Ingestion points: The workflow in SKILL.md and SKILL.ko.md explicitly reads external documentation for analysis and refactoring in Phase 1.
- Boundary markers: The skill instructions do not specify the use of XML delimiters or 'ignore' directives when interpolating the content of these external documents into the agent's context.
- Capability inventory: The agent is equipped with tools including Read, Edit, Glob, Grep, and Bash, as well as the ability to spawn specialized sub-agents via the Task tool.
- Sanitization: There is no evidence of content validation or sanitization routines to filter potential malicious instructions embedded in the processed documentation.
Audit Metadata