execute-icebox-subtask

Pass

Audited by Gen Agent Trust Hub on Apr 8, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill uses the agkan CLI tool to manage task workflows. The operations (get, update) are consistent with the stated purpose of reviewing and promoting icebox tasks.
  • [COMMAND_EXECUTION]: Executes shell commands using the agkan tool and standard utilities like cat. These are used for task retrieval and status updates.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external task data (via agkan task get). While this represents a surface for indirect prompt injection if task content contains malicious instructions, the skill's capabilities are limited to task status updates within the agkan system.
  • Ingestion points: Reads task content from the agkan database (SKILL.md).
  • Boundary markers: Standard shell interpolation is used; instructions provide guidance on evaluation.
  • Capability inventory: Task retrieval and status updates via the agkan CLI (SKILL.md).
  • Sanitization: Content is written to a temporary file via heredoc to maintain integrity before update.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 8, 2026, 06:42 AM