prompting-pattern-library
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [No Code] (SAFE): The skill is composed entirely of Markdown documentation files (README.md, SKILL.md, and references/model-quirks.md). There are no scripts, binaries, or automation logic included.
- [Prompt Injection] (SAFE): The content provides educational prompting patterns and examples. It does not contain instructions designed to override agent security boundaries or extract system prompts.
- [Data Exposure & Exfiltration] (SAFE): No hardcoded credentials, sensitive file paths, or network-enabled functions were detected in any of the files.
- [Indirect Prompt Injection] (SAFE): The skill identifies ingestion points where a user might pass external data to a prompt (e.g., [data] placeholders). However, the skill provides boundary markers (like XML tags) to mitigate risks and lacks the dangerous capabilities (like file system writes or network calls) required for a high-impact attack.
Audit Metadata