ai-prompt-writer
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill functions solely as an instructional guide for prompt engineering and does not involve any operations that could compromise the host environment or expose sensitive data.
- [NO_CODE]: The skill is comprised of static markdown files (SKILL.md, references/prompt-techniques-john.md, and references/training-guide-modules.md) and does not include any scripts, executable binaries, or package manager configurations.
- [INDIRECT_PROMPT_INJECTION]: The skill accepts user-provided context and source material as inputs to generate prompts, creating a surface for indirect prompt injection. However, the risk is negligible as the skill lacks any capabilities to perform network requests, modify the file system, or execute shell commands.
- Ingestion points: Required input fields in SKILL.md for brand context, audience, and source material.
- Boundary markers: The training reference file (references/training-guide-modules.md) recommends the use of '###' separators to distinguish instructions from content.
- Capability inventory: None. No tools for network, file, or system access are defined or utilized.
- Sanitization: No explicit input validation or sanitization is performed.
Audit Metadata