agent-cli-developer
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides instructions and best practices for developing command-line tools. It does not contain any executable code, sensitive data access, or malicious patterns.
- [INDIRECT_PROMPT_INJECTION]: The skill includes the
$ARGUMENTSplaceholder, which acts as a data ingestion point for the subagent. While this creates a surface for indirect prompt injection if untrusted data is passed to the agent, the skill itself is a generic development assistant and contains no instructions to bypass safety guidelines or perform unauthorized actions. Standard agent guardrails apply to the processing of these arguments.
Audit Metadata