academic-language-sentence-frame-generator

Pass

Audited by Gen Agent Trust Hub on May 13, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No security threats such as malicious code, obfuscation, or data exfiltration were found in the skill documentation or prompt logic.
  • [PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection as it interpolates user-controlled data into the system prompt.
  • Ingestion points: Untrusted data enters via template variables in SKILL.md, specifically task_type, subject_area, student_level, language_proficiency, student_profiles, specific_content, and output_mode.
  • Boundary markers: No explicit delimiters or encapsulation tags are used to isolate user-provided text from instructions.
  • Capability inventory: The skill is restricted to text generation only and does not invoke any external tools, system commands, or network APIs.
  • Sanitization: No input validation or escaping is applied to the template variables.
Audit Metadata
Risk Level
SAFE
Analyzed
May 13, 2026, 04:53 AM
Security Audit — agent-trust-hub — academic-language-sentence-frame-generator