prompt-writing
Pass
Audited by Gen Agent Trust Hub on May 18, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill uses the
astriaCLI for its operations, which is restricted to theastria:*namespace as defined in theallowed-toolsfrontmatter. - [SAFE]: Implements a human-in-the-loop process by requiring the agent to show generated prompts to the user for review and approval before execution.
- [SAFE]: No attempts at prompt injection, obfuscation, or unauthorized data access were found. All external interactions are limited to the vendor's own CLI tool.
Audit Metadata