goal-setting-protocol-designer
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE]: The skill consists entirely of a markdown file containing YAML frontmatter and a text-based prompt. It does not ship with any scripts, executables, or configurations that would allow for code execution on the user's machine.
- [INDIRECT_PROMPT_INJECTION]: The skill defines a surface for indirect prompt injection by ingesting untrusted user input into the prompt.
- Ingestion points: The skill processes several input fields in
SKILL.mdincludinglearning_context,student_level,timeframe,goal_type,student_profiles,success_criteria, andsubject_area. - Boundary markers: The inputs are delimited by bold markdown headers (e.g., Learning context:) but do not include explicit instructions to the model to disregard instructions contained within the data.
- Capability inventory: Analysis of the skill reveals no capabilities for file system access, network operations, subprocess spawning, or dynamic code execution.
- Sanitization: The skill does not perform any validation or escaping of the input strings before they are sent to the model.
Audit Metadata