Skip to content

Repository files navigation

Agent Security Radar

Validate radar catalog

A practical research radar for turning agent-security papers and incidents into engineering controls.

Latest radar

2026-07-26 · Authorization, malicious issues, jailbreak evaluation, and RAG salience

Five direct-source papers are mapped to the agent lifecycle with facts, engineering interpretation, and explicit unknowns.

Use the repository

Resource Purpose
Latest report A reviewed seven-day radar with exactly five items
Risk taxonomy Threats and controls across the agent lifecycle
Research method Source, inclusion, evidence, and stop rules
Paper catalog Machine-readable metadata for reviewed papers
Catalog schema JSON Schema for structure and lifecycle vocabulary
Report template Reusable daily or weekly format
Catalog validator Lightweight structural validation
Validation tests Regression coverage for date and lifecycle rules
Contributing How to propose a paper or correction

Scope

The radar tracks risks created when AI agents read untrusted content, call tools, retain memory, coordinate with other agents, or act in external systems.

Area Core question
Prompt injection Can untrusted content redirect the agent?
Tool use Is every capability scoped, authorized, and auditable?
Memory and retrieval Can poisoned, true-but-misleading, or sensitive context persist?
Multi-agent systems Can authority or misinformation propagate between agents?
Data security Can secrets cross an unintended boundary?
Execution safety Does uncertainty stop real-world actions?

Lifecycle model

Input → Context → Planning → Tool selection → Authorization
      → Execution → External state → Reconciliation → Memory

Findings are mapped to one or more stages rather than grouped under an undifferentiated “AI safety” label.

Editorial rules

  • Prefer papers, advisories, repositories, and incident reports from direct sources.
  • Keep a fixed research window and avoid backfilling weak items to reach a count.
  • Separate source-reported facts, engineering interpretation, and unknowns.
  • Do not treat benchmark performance as production safety.
  • Link each recommended control to a concrete risk and lifecycle stage.
  • Keep consequential actions fail-closed when identity, authorization, data, or external state is uncertain.

Validate the catalog

check-jsonschema --schemafile data/papers.schema.json data/papers.json
python3 -m unittest discover -s tests -v
python3 scripts/validate_catalog.py data/papers.json

The validator checks structure, unique identifiers, direct HTTPS sources, and the exact-five invariant used by the current public report.

Direct sources first. Facts, inference, and unknowns stay separate.

License

  • Code, tests, workflows, and schema implementation: Apache-2.0
  • Reports, catalog data, templates, and research documents: CC BY 4.0

About

A practical radar for agent-security papers, incidents, and engineering controls.

Topics

Resources

Contributing

Security policy

Stars

0 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages