occ-diagnose
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes
npxto run@ruvnet/open-claude-code@2.1.3for version and help verification. This is a vendor-owned package and is central to the skill's diagnostic function. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to inspect skill definition files located in
.claude/skills/and~/.claude/skills/. This introduces a surface for indirect injection from local configuration files; however, the skill includes explicit mandates to sanitize output and redact sensitive provider data.
Audit Metadata