prompt-improver
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [Prompt Injection] (SAFE): No instructions designed to override agent behavior or bypass safety filters were found. The skill focuses on pedagogical prompt improvement.- [Data Exposure & Exfiltration] (SAFE): No hardcoded credentials or sensitive file paths (e.g., SSH keys, AWS configs) are present. There are no network operations to non-whitelisted domains.- [External Downloads] (SAFE): The skill does not perform any external package installations or remote script executions. References to external documentation are for informational purposes only.- [Indirect Prompt Injection] (LOW): 1. Ingestion points: User-provided prompts passed to the /prompt-improver command. 2. Boundary markers: None present. 3. Capability inventory: No scripts or dangerous capabilities (subprocesses, file writes) are included in the skill. 4. Sanitization: Not applicable as the skill only provides text transformation guidance.
Audit Metadata