zj-write-a-skill
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of instructional text, templates, and architectural advice for skill development. No malicious behavior, data exfiltration, or obfuscation was detected.- [INDIRECT_PROMPT_INJECTION]: The skill establishes a workflow for gathering user requirements to generate new files and scripts. This pattern involves processing untrusted user input, but it is the primary intended function of the skill and does not include unsafe processing logic or capability escalation within the skill body itself.
Audit Metadata