Private MCP result is reused across authorization contexts
A shared cache delivers caller-specific protocol data outside the authorization context that produced it.
Candidate CWE: CWE-524 · CWE-863
Test hypothesis#
Warm a private owned B resource; repeat the same operation as A and compare with cold-cache denial. Separately inspect whether state-bearing MRTR retry results are incorrectly cached.
Evidence required#
Record method/parameters, authorization-context fingerprints, cache hints, cache hit/miss and the newly exposed private marker.
Rule out false positives#
Identical public tool lists, hints without a demonstrated shared result, or private content legitimately accessible to both callers do not prove exposure.
Playbook and command references#
- AI state: memory, resumed work, retries and private caches — Test persistent context, task ownership, MCP request-state integrity, duplicate effects and caches across identities and time.
- RAG isolation: ingestion, retrieval, citations and revocation — Trace document authorization through vector search, generated answers, citation downloads, caches and sharing changes.
Find the associated command snippets
Referenced by these target playbooks#
Report checklist#
- Capture the affected version, configuration, identities, and object ownership.
- Preserve a valid baseline and a negative control.
- Reproduce the forbidden data access, action, or state change on controlled fixtures.
- Explain the intended security rule and why the observed behavior violates it.
- State prerequisites, uncertainty, cleanup, and the smallest demonstrated impact.
Conditional ATT&CK mapping#
No direct ATT&CK mapping selected. Record the weakness and demonstrated impact without forcing an adversary-behavior classification. See the mapping guide.