todo-list-builder
Pass
Audited by Gen Agent Trust Hub on May 6, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill instructions specify using
git committo version control changes made to theTODO_LIST.mdfile. This is a standard and expected operation for a developer-oriented task. - [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it processes untrusted project data (markdown and code files) using sub-agents.
- Ingestion points: All
.mdfiles and source code files within the project environment. - Boundary markers: Absent. The instructions do not define delimiters for the ingested content.
- Capability inventory: The skill is capable of reading project files, writing to
TODO_LIST.md, and executinggit commitcommands. - Sanitization: None. The skill does not explicitly validate or sanitize the content of the files it reads before processing them with sub-agents.
Audit Metadata