prompt-engineering
Pass
Audited by Gen Agent Trust Hub on Mar 31, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides instructional content and Python helper functions for creating prompt templates. It does not perform any network operations, sensitive file access, or command execution. All identified patterns are standard for prompt engineering education.\n- [PROMPT_INJECTION]: The skill defines templates for interpolating untrusted data into LLM prompts, creating an indirect prompt injection surface.
- Ingestion points: Placeholders in SKILL.md such as {context}, {code}, and {input} ingest external data.
- Boundary markers: Markdown code blocks (triple backticks) are used in some templates to delimit input data.
- Capability inventory: None; the skill only generates strings and does not invoke subprocesses, network operations, or file system writes.
- Sanitization: No input sanitization or validation is implemented before data interpolation.
Audit Metadata