prompt-engineering-library
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill defines a purely instructional set of templates and formulas for marketing copy generation. No malicious patterns, obfuscation, or unauthorized access attempts were found.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user data such as brand voice descriptors and social media messages (SKILL.md). It addresses potential injection risks by instructing the use of boundary markers (### separators) and structured placeholders ({{double-brace}}). The lack of high-risk capabilities, such as file system writing or network operations, ensures the skill remains secure.
Audit Metadata