AI Agent Security Cheat Sheet¶
OWASP. (2025). AI Agent Security Cheat Sheet.
Cited by¶
1 citation across 1 artifact.
Each citation links to the sentence it supports in the citing article.
Primes¶
- Rule of Least Power (Minimum Sufficient Capability)
- From security to AI tool design, agent tools should be scoped to least capability — read-only by default, narrow targets, rate limits — before any write or shell access is granted.
This sourceRecommends scoping AI-agent tools to least capability — default-deny, read-only by default, narrow targets, just-in-time/ephemeral credentials, human-in-the-loop — before granting write or shell access.
- From security to AI tool design, agent tools should be scoped to least capability — read-only by default, narrow targets, rate limits — before any write or shell access is granted.
Verification¶
This reference passed the adversarial substantiation pipeline: it was checked to exist and to support the claim it is attached to. See how references were verified.
Registry ID ref:18a89bd5e26f · see in the full table