prompt-engineering-expert
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted user data in the form of prompts submitted for evaluation.
- Ingestion points: User-provided strings for analysis, documented in
README.md,CLAUDE.md, andexamples/EXAMPLES.md. - Boundary markers: The skill instructions recommend using XML tags and structured placeholders (e.g.,
[YOUR PROMPT]) to delimit user content. - Capability inventory: The skill defines its scope as "Analysis Only" and explicitly states it does not execute code or run prompts. It has no access to subprocess tools, network operations, or file-writing capabilities.
- Sanitization: Input content is not explicitly sanitized, but the lack of exploitable tools effectively mitigates the risk of indirect injection.
- [SAFE]: The skill provides high-quality educational content based on official documentation. All external references are to trusted or well-known sources, such as Anthropic's official blog and documentation, and reputable prompt engineering educational sites.
Audit Metadata