ContextForge accepts JSON Schemas for registered tools, prompts or federated tool surfaces. An actor allowed to register a schema can embed a regular expression with catastrophic backtracking in pattern or patternProperties and cause expensive validation on later arguments. The danger appears when the gateway evaluates otherwise legitimate tool arguments…
Inspect the ClaimsCase · DiggingBeagle record
An MCP tool schema could carry an expensive regular expression that blocks the shared ContextForge worker
ContextForge accepts JSON Schemas for registered tools, prompts or federated tool surfaces. An actor allowed to register a schema can embed a regular expression with catastrophic backtracking in pattern or patternProperties and cause expensive validation on later arguments.
Public disclosure: Nov 13, 2026
An authenticated actor has tool/prompt registration rights or can supply a federated schema that reaches the validator.
At a glance
A schema is stored as trusted validation policy despite attacker-selected regex work, letting later tool calls consume worker CPU.
Read the implicationsThis is a security gap in AI tool metadata admission, not a general inability of the language model to parse a malicious prompt.
Limits and uncertaintyFull account
ContextForge accepts JSON Schemas for registered tools, prompts or federated tool surfaces. An actor allowed to register a schema can embed a regular expression with catastrophic backtracking in pattern or patternProperties and cause expensive validation on later arguments.
The danger appears when the gateway evaluates otherwise legitimate tool arguments against the retained attacker-influenced schema. The tool registration event and subsequent resource exhaustion may be separated in time or occur under different callers.
IBM reports CVE-2026-94407 for v1.0.0 through v1.0.11 and recommends upgrade to 1.1.0. This establishes a code-level denial-of-service risk, not a confirmed service outage or model-driven misuse.
This is a security gap in AI tool metadata admission, not a general inability of the language model to parse a malicious prompt.
Mechanism and trust boundary
- 01
Starting condition
An authenticated actor has tool/prompt registration rights or can supply a federated schema that reaches the validator.
Boundary: precondition and attacker capability
- 02
Trust boundary crossed or evaluated
The danger appears when the gateway evaluates otherwise legitimate tool arguments against the retained attacker-influenced schema. The tool registration event and subsequent resource exhaustion may be separated in time or occur under different callers.
Boundary: mechanism
- 03
Observed consequence
A schema is stored as trusted validation policy despite attacker-selected regex work, letting later tool calls consume worker CPU.
Boundary: observed effect and limitations
Claims & evidence
CLM-NOV15-CF94407-MECHContextForge accepts JSON Schemas for registered tools, prompts or federated tool surfaces. An actor allowed to register a schema can embed a regular expression with catastrophic backtracking in pattern or patternProperties and cause expensive validation on later arguments. The danger appears when the gateway evaluates otherwise legitimate tool arguments against the retained attacker-influenced schema. The tool registration event and subsequent resource exhaustion may be separated in time or occur under different callers.supported
Basis: reported finding
- supportsIBM bulletin: registered tool-schema ReDoS in ContextForgevendor statement
IBM Security Bulletin CVE-2026-94407, JSON Schema pattern/patternProperties and 1.1.0 remediation
CLM-NOV15-CF94407-SCOPEIBM reports CVE-2026-94407 for v1.0.0 through v1.0.11 and recommends upgrade to 1.1.0. This establishes a code-level denial-of-service risk, not a confirmed service outage or model-driven misuse. This is a security gap in AI tool metadata admission, not a general inability of the language model to parse a malicious prompt.supported
Basis: reported finding
- supportsIBM bulletin: registered tool-schema ReDoS in ContextForgevendor statement
Primary disclosure: results, scope and limitations
Implications
A schema is stored as trusted validation policy despite attacker-selected regex work, letting later tool calls consume worker CPU.
Controls and mitigations
- Enforce schema pattern complexity and execution budgets before accepting new tools.
- Upgrade to fixed gateway versions and test admission on hostile patterns without allowing unbounded validation of shared worker traffic.
Unknowns and contradictions
- This is a security gap in AI tool metadata admission, not a general inability of the language model to parse a malicious prompt.
Sources and citation
Material revision history
- Nov 15, 2026 · Canonical change recorded · new in release · revision 250