U.S. National Institute of Standards and Technology · AI RMF 1.0 (NIST AI 100-1)
NIST AI Risk Management Framework: real-world incidents for each item
MAP 5.1 asks organizations to estimate the likelihood and magnitude of impacts using, among other data, past uses of AI systems in similar contexts and public incident reports. CollectSEA makes that evidence searchable at design time.
Official NIST AI RMF- MAP 5.1
Estimate impacts from past uses and public incident reports
Likelihood and magnitude of each identified impact are identified and documented based on expected use, past uses of AI systems in similar contexts, public incident reports and other data.
- Indirect prompt injection changes agent behavior
- AI action exceeds its intended scope
- Privileged action without an enforceable approval gate
- Retry amplification and runaway resource consumption
- Prompt injection makes GitHub Copilot turn off its own confirmations and run commands (CVE-2025-53773)2025
- Prompt injection in a README plus weak allow-list matching lets Gemini CLI silently run attacker commands (2025)2025
- Hidden instructions in a support ticket make an MCP-connected assistant expose private SQL tables (Supabase MCP, 2025)2025
- EchoLeak: zero-click prompt injection lets a crafted email exfiltrate Microsoft 365 Copilot data (2025)2025
- Prompt injection in a public GitHub issue makes an MCP-connected agent leak private repository data (2025)2025
- GitHub Actions injection leaks Nx's npm token; malicious packages use local AI coding tools to hunt for secrets (2025)2025
and 13 more in the linked patterns.
- MANAGE 4.3
Track and communicate incidents and errors
Incidents and errors are communicated to relevant AI actors, and processes for tracking, responding to and recovering from them are followed and documented.
- Call and text records of nearly all AT&T wireless customers taken from a third-party cloud workspace (2024)2024
- Stolen credential opens Okta's support system, where uploaded HAR files held customer session tokens (2023)2023
- GitHub's RSA SSH host private key briefly exposed in a public repository (2023)2023
- Malware steals an engineer's SSO session and exposes CircleCI customer secrets (2023)2023
- Phishing impersonating a CI vendor yields GitHub credentials and 130 source-code repositories (Dropbox, 2022)2022
- SMS phishing of employees leads to compromise of Twilio customer accounts (2022)2022
and 10 more in the linked patterns.
Mappings are CollectSEA's own analysis and are not produced or endorsed by U.S. National Institute of Standards and Technology. Item names and summaries paraphrase the official text; consult the source for the authoritative wording.