writing-system-prompts
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides documentation and guidelines for the agent to follow when assisting users with system prompt engineering. No malicious instructions or bypass attempts were found.
- [SAFE]: No external dependencies, network operations, or sensitive file accesses are present. The skill contains no executable code.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze user-provided content. 1. Ingestion points: Input via the '' argument defined in the frontmatter. 2. Boundary markers: Absent. 3. Capability inventory: No tools for file-writing, network access, or command execution are defined or requested. 4. Sanitization: Absent. The risk is minimal as the skill lacks exploitable capabilities.
Audit Metadata