nanobana-prompts
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No evidence of malicious behavior, credential harvesting, or remote code execution was found. The skill operates entirely within the text processing domain of the AI agent.
- [INDIRECT_PROMPT_INJECTION]: Ingestion points: Untrusted user data is ingested in workflows/refine-prompt.md, workflows/adapt-style.md, and workflows/describe-to-prompt.md. Boundary markers: No explicit markers are used to delimit user input. Capability inventory: No shell commands, file system access, or network requests are present in any script. Sanitization: No content filtering or validation is performed. The lack of dangerous capabilities mitigates the risk of system exploitation.
Audit Metadata