todo-triage
Pass
Audited by Gen Agent Trust Hub on Apr 2, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill reads and presents findings from todo files located in '.context/systematic/todos/' and 'todos/'. This ingestion of potentially untrusted data represents an indirect prompt injection surface. * Ingestion points: File contents from '.context/systematic/todos/' and 'todos/' directories. * Boundary markers: None present to distinguish untrusted data from system instructions. * Capability inventory: Includes file system operations such as renaming and deleting files. * Sanitization: No sanitization or filtering is performed on the ingested todo content.
- [COMMAND_EXECUTION]: The workflow requires the agent to perform file system operations including renaming and deleting files. * Evidence: Instructions in the 'Handle Decision' section specify renaming files from 'pending' to 'ready' and deleting files when they are skipped.
Audit Metadata