NYC

agile-product-owner

Pass

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: LOWCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [Unverifiable Dependencies & Remote Code Execution] (LOW): The skill documentation references a local script scripts/user_story_generator.py. While the script's source code is not provided in the input, the documented usage for generating INVEST-compliant user stories and planning sprints is standard and consistent with the skill's stated purpose.\n- [Indirect Prompt Injection] (LOW): The skill processes untrusted user-provided data (epics) to generate structured output. Mandatory Evidence Chain: 1. Ingestion points: User-provided epics processed by the generator script. 2. Boundary markers: Absent from the documentation. 3. Capability inventory: Execution of local Python scripts and LLM reasoning/generation. 4. Sanitization: Not documented. The risk is considered low because the untrusted input primarily influences text generation rather than enabling file system modifications or network access.
Audit Metadata
Risk Level
LOW
Analyzed
Feb 16, 2026, 09:24 AM