agent-installer
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides instructions for the agent to assist users in selecting and organizing agent files within a specific environment (.codex/agents/). It focuses on generating manual copy/setup steps, verification commands, and rollback guidance.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-defined objectives to recommend agent sets and installation scopes. While it does not explicitly define boundary markers or sanitization for these inputs, the output is intended for manual review and execution by the user, which mitigates the risk of automated exploitation.
- Ingestion points: User objectives provided at runtime in SKILL.md.
- Boundary markers: None explicitly defined in the instructions.
- Capability inventory: Generation of file placement instructions and configuration prerequisites; no direct file-writing or command execution capabilities are invoked by the skill itself.
- Sanitization: None detected in the instructions.
Audit Metadata