developer-onboarding
Pass
Audited by Gen Agent Trust Hub on Sep 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists of instructional content and configuration files designed to assist in creating setup guides. A thorough analysis of the repository files revealed no malicious intent, command execution, or data exfiltration patterns.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted content from a repository, such as setup scripts, package files, and documentation (ingestion points identified in SKILL.md, Core Workflow step 2). While this creates a surface for indirect prompt injection, the skill's capability inventory is limited to markdown generation. Furthermore, it includes specific sanitization guidelines, such as instructions to never invent commands and to exclude private credentials, which mitigates potential risks from malicious repo content.
Audit Metadata