agent-research
Pass
Audited by Gen Agent Trust Hub on Aug 11, 2026
Risk Level: SAFE
Full Analysis
- [DATA_EXFILTRATION]: The skill uses the Nimble Agent API (app.nimbleway.com), which is the official platform for the skill's author. It does not attempt to exfiltrate data to unauthorized third-party domains.
- [CREDENTIALS_UNSAFE]: The skill correctly instructs users to manage the
NIMBLE_API_KEYvia a.envfile and includes explicit instructions never to print or echo the key in the agent's output. - [DATA_EXPOSURE]: The skill mentions that researched web content is untrusted data and explicitly warns against following instructions found within that content (Indirect Prompt Injection mitigation).
- [COMMAND_EXECUTION]: No shell command execution or risky subprocess spawning is present in the instructions.
Audit Metadata