agnes-ai-generation

Pass

Audited by Gen Agent Trust Hub on Jun 1, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: All network activity is restricted to the official Agnes AI API endpoint at apihub.agnes-ai.com. These operations are consistent with the skill's stated purpose of providing content generation capabilities.
  • [SAFE]: The skill implements secure credential handling by retrieving API keys from environment variables (AGNES_API_KEY, AGNES_API_TOKEN, or APIHUB_AGNES_API_KEY). No hardcoded secrets or unsafe storage methods were identified.
  • [SAFE]: The script uses standard Python libraries (urllib, json, argparse) to interact with the API. There is no evidence of dynamic code execution (eval/exec), privilege escalation (sudo), or persistence mechanisms (cron/startup scripts).
  • [PROMPT_INJECTION]: The skill processes user-supplied prompts and image URLs which are passed to the Agnes AI models. This represents a standard surface for indirect prompt injection where a third-party model might return instructions; however, the skill itself does not execute these outputs as system commands, mitigating the risk to the local environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 1, 2026, 10:32 AM
Security Audit — agent-trust-hub — agnes-ai-generation