AI Agent Security Cheat Sheet

OWASP. (2025). AI Agent Security Cheat Sheet.

Type

Standard

Intellectual base

Reference work

Year

2025

Link

https://cheatsheetseries.owasp.org/cheatsheets/AI_Agent_Security_Cheat_Sheet.html

Cited from

computer_science

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.

    Supported in partVerified against the work's full text

    The cheat sheet backs least-privilege tool scoping (minimum tools, read-only vs write, specific resources, restricted shell, output rate limits) but not 'read-only by default' as a gating order.

    “Implement per-tool permission scoping (read-only vs. write, specific resources).”

    Read by an automated reader; not a human review. How support was checked

Verification

Does it exist? Not checked yet. This entry carries no identifier to resolve. It was extracted from the citation as written in the article, normalized, and deduplicated against the rest of the registry.

Does it back the claim? Read against the text for 1 of 1 citation: 1 supported in part. Each verdict is shown under its citation below, with what in the work backs the sentence.

Support is checked per citation rather than per work — the same source can be cited soundly in one article and wrongly in another. Per-citation recording began recently, so a citation with no recorded check is a gap in the record rather than evidence it went unchecked.

See how references were verified.

Registry ID ref:18a89bd5e26f · see in the full table