infra-architect
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE] (SAFE): The skill contains no executable scripts, binaries, or automation commands. It is purely informational markdown.
- [PROMPT_INJECTION] (SAFE): No malicious override patterns, jailbreak attempts, or instructions to ignore system safety filters were detected. The use of role-play instructions is within normal operational bounds for AI agents.
- [EXTERNAL_DOWNLOADS] (SAFE): No remote URLs, script downloads (e.g., curl/wget), or external package dependencies (pip/npm) are present.
- [DATA_EXFILTRATION] (SAFE): No patterns related to reading sensitive files (~/.ssh, ~/.aws) or sending data to external endpoints were found.
- [INDIRECT_PROMPT_INJECTION] (SAFE): While the skill references external local files (e.g., references/patterns.md), the skill itself lacks any capabilities (like code execution or network access) that could be exploited by malicious content within those reference files.
Audit Metadata