skills/gendosu/agkan-skills/agkan/Gen Agent Trust Hub

agkan

Pass

Audited by Gen Agent Trust Hub on Apr 8, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the agkan CLI tool for task management and process monitoring via the agkan ps command.
  • [PROMPT_INJECTION]: The skill has an indirect prompt injection surface through its file ingestion capabilities.
  • Ingestion points: The --file flag in the task add and task update commands, as well as the import command (SKILL.md).
  • Boundary markers: No delimiters or instructions to ignore embedded commands are provided for content read from external files.
  • Capability inventory: The skill enables full access to task management, tagging, and local process monitoring through the agkan toolset.
  • Sanitization: No sanitization or validation of content from external files is described.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 8, 2026, 06:43 AM