agents-brain

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 1.00). The skill runs scripts/fetch-guidance.sh at runtime to download official prompting guides which will be read and used to shape agent prompts — specifically the script fetches https://developers.openai.com/api/docs/guides/prompt-guidance-gpt-5p6.md and https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-fable-5.md, so external content directly influences agent instructions.