agile-product-owner
Pass
Audited by Gen Agent Trust Hub on Jun 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local Python script located at scripts/user_story_generator.py. This script is used to automate the generation of INVEST-compliant user stories and sprint plans based on user input.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes untrusted user requirements to generate structured product documentation. 1. Ingestion points: User input provided for requirements, epics, or sprint goals in SKILL.md. 2. Boundary markers: No specific delimiters or safety instructions are used to isolate user input from the skill's logic. 3. Capability inventory: Execution of local Python scripts and generation of complex text outputs. 4. Sanitization: There is no evidence of input validation or sanitization before processing.
Audit Metadata