tree-generator
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to ingest untrusted external data to generate AI agent instructions.
- Ingestion points: The skill processes
domain_map.yaml,skill_spec.md, and raw library documentation or source code to build a skill tree. - Boundary markers: There are no explicitly defined boundary markers or instructions to wrap ingested content in delimiters to prevent the agent from following instructions embedded in the source data.
- Capability inventory: The skill has the capability to write multiple markdown and YAML files to the filesystem and modify project configuration via tools like
intent edit-package-json. - Sanitization: The instruction generation process does not specify methods for sanitizing or escaping content extracted from external documentation or source code before it is interpolated into the generated instruction files.
Audit Metadata