indexion-agent-orient
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The workflow involves reading a task.md file and generating orientation briefs that are intended to be pasted into other agent configuration contexts like CLAUDE.md or AGENTS.md. This path allows potentially malicious instructions within a task description to be promoted into an agent's primary instruction set.
- [COMMAND_EXECUTION]: The skill requires the execution of multiple shell commands using the indexion CLI tool to build orientation maps and query documentation graphs.
Audit Metadata