agently-request

Pass

Audited by Gen Agent Trust Hub on May 28, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill acts as a documentation and implementation guide for the Agently framework, promoting structured and maintainable agent development.
  • [CREDENTIALS_UNSAFE]: No hardcoded secrets were found. The skill explicitly recommends using environment variable placeholders (${ENV.xxx}) for provider settings and uses standard "YOUR_API_KEY" placeholders in example scripts such as examples/model-setup-minimal.py.
  • [REMOTE_CODE_EXECUTION]: The documentation in references/output-control.md and SKILL.md describes a functional pattern where models generate code (Python, Bash, SQL) to be executed by tools for complex arithmetic or data processing. This is presented as a design recommendation for tool capabilities to improve accuracy, rather than an unauthorized code execution vulnerability.
Audit Metadata
Risk Level
SAFE
Analyzed
May 28, 2026, 09:05 AM
Security Audit — agent-trust-hub — agently-request