Skip to main content

ai-safe2-secure-build-copilot

Implements the AI SAFE² framework to ensure secure, compliant AI systems and workflows, enhancing governance and risk management.

Install this skill

or
85/100

Security score

The ai-safe2-secure-build-copilot skill was audited on Feb 19, 2026 and we found 11 security issues across 3 threat categories. Review the findings below before installing.

Categories Tested

Security Issues

low line 208

Webhook reference - potential data exfiltration

SourceSKILL.md
208- [List where data enters/exits: user input, API calls, file uploads, webhooks]
medium line 342

Prompting for API key/token input

SourceSKILL.md
342"code_fix": "# Use environment variable\nimport os\nopenai.api_key = os.getenv('OPENAI_API_KEY')\n# Remove from prompt\nprompt = f'Search for: {query}'",
low line 857

External URL reference

SourceSKILL.md
857- Toolkit Download: https://cyberstrategyinstitute.com/AI-Safe2/
low line 862

External URL reference

SourceSKILL.md
862- OWASP Top 10 for LLMs: https://owasp.org/www-project-top-10-for-large-language-model-applications/
low line 863

External URL reference

SourceSKILL.md
863- MITRE ATLAS: https://atlas.mitre.org/
low line 864

External URL reference

SourceSKILL.md
864- NIST AI RMF: https://www.nist.gov/itl/ai-risk-management-framework
low line 865

External URL reference

SourceSKILL.md
865- ISO/IEC 42001: https://www.iso.org/standard/81230.html
low line 866

External URL reference

SourceSKILL.md
866- MIT AI Risk Repository: https://airisk.mit.edu/
low line 870

External URL reference

SourceSKILL.md
870- Guardrails AI: https://www.guardrailsai.com/
low line 871

External URL reference

SourceSKILL.md
871- LangChain Security: https://python.langchain.com/docs/security
low line 872

External URL reference

SourceSKILL.md
872- OpenSSF Sigstore: https://www.sigstore.dev/
Scanned on Feb 19, 2026
View Security Dashboard