prompt-literacy-sequence-designer

Pass

Audited by Gen Agent Trust Hub on Jun 14, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface (Category 8) by interpolating user-supplied strings directly into the agent's core instructions.
  • Ingestion points: Data provided via the input_schema fields (subject_area, student_level, ai_task_type, prompt_literacy_focus, and common_student_prompts) are injected into the instructions using {{variable}} syntax in SKILL.md.
  • Boundary markers: Absent. The prompt template does not use delimiters, XML tags, or triple quotes to isolate interpolated user content from the instructional logic.
  • Capability inventory: The agent maintains full tool access and model invocation capabilities (disable-model-invocation: false).
  • Sanitization: No validation or sanitization mechanisms are defined to filter or escape potentially malicious instructions embedded in the user inputs.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 14, 2026, 11:56 AM
Security Audit — agent-trust-hub — prompt-literacy-sequence-designer