tutorial-engineer

Pass

Audited by Gen Agent Trust Hub on Aug 8, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The instructions and metadata are focused entirely on pedagogical design and tutorial structure. No unsafe tool usage, remote code execution, or credential harvesting patterns were found.
  • [PROMPT_INJECTION]: The skill processes user-supplied code to generate tutorials, creating a surface for indirect prompt injection. However, the risk is negligible as the skill does not utilize tools for network access, file system modification, or command execution that could be exploited by such an injection.
  • Ingestion points: User-provided 'Topic or Code' input specified in the 'Task-Specific Inputs' section of SKILL.md.
  • Boundary markers: None defined; the instructions do not explicitly tell the agent to ignore instructions embedded in the input code.
  • Capability inventory: No dangerous capabilities (network, shell, file-write) are included in the skill's instruction set.
  • Sanitization: No sanitization or validation of the input source code is defined in the instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 8, 2026, 03:34 PM
Security Audit — agent-trust-hub — tutorial-engineer