The safeguards map / 3.4 Guardrails
OWASP Agent Memory Guard
Drafted with AI
Drafted with AI from the cited sources under the direction of UnGovr staff. UnGovr holds editorial responsibility for this page. How this site is made
A Python library that screens every write to an AI agent's memory store with detectors and a YAML policy that can allow, redact, quarantine or block it.
Where it sits
3.4 Guardrails (primary): Screens each operation on an agent's memory store with built-in detectors and a policy that maps findings to allow, redact, quarantine or block.
Agent Memory Guard sits between the agent and its memory store, screening every operation through a pipeline of detectors and a declarative policy.
captured
built-in detectors for prompt injection, secret/PII leakage, protected-key modifications, size anomalies
captured
YAML-defined rules map findings to actions
captured
Facts
- Concern
- security
- Names the law
- no
- Subject
- agent
- Used by
- those who make itthose who run it
- Runs
- at runtime
- Policy comes from
- vendor defaultsowner-entered settings
Handoffs
None recorded. A mapped entry with no handoff is here for its foundation home.
Every quote is verbatim from a stored capture of the page linked under it. Placement is our reading of the product's own documentation; no publisher has reviewed or endorsed it. Rows CC BY 4.0. Names, marks and logos belong to their owners; logos identify each product and are not part of the dataset.