resolve-todo-parallel
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes 'todo' files which are external data sources that may contain instructions intended to manipulate agent behavior.
- Ingestion points: Workflow Step 1 in SKILL.md instructs the agent to read all candidate todo files from the repository.
- Boundary markers: There are no explicit delimiters or instructions to treat the todo content as untrusted data.
- Capability inventory: The agent is authorized to modify repository files, rename files, and run 'focused checks' (command execution) based on the requirements defined in the todo files.
- Sanitization: The workflow does not include any validation or sanitization of the todo file content before it influences agent actions.
Audit Metadata