fix: upgrade js-yaml to 3.15.0 (CVE-2026-53550)

[Copilot]

js-yaml ≤3.14.2 has a quadratic-complexity DoS in YAML merge-key (<<:) handling — repeated aliases in a merge sequence cause O(K×M) work while input is O(K+M). Fixed in 3.15.0 via deduplication of merge sources.

js-yaml is a transitive dependency via @istanbuljs/load-nyc-config (Jest/nyc coverage tooling). Application code parses no YAML, so there is no direct exploit surface; this update resolves the scanner finding.

Changes

• package.json — added "js-yaml": "3.15.0" to the existing overrides block to pin the transitive dep to the patched version
• package-lock.json — regenerated; node_modules/js-yaml now resolves to 3.15.0

Original prompt

---

This section details the Dependabot vulnerability alert you should resolve

<alert_title>JS-YAML: Quadratic-complexity DoS in merge key handling via repeated aliases</alert_title>
<alert_description>### Summary
A crafted YAML document can trigger algorithmic CPU exhaustion in js-yaml merge-key processing (<<) by repeating the same alias many times in a merge sequence.
This causes quadratic parse-time behavior relative to input size and can block a Node.js worker/event loop for seconds with a relatively small payload (tens of KB), resulting in denial of service.

Details

The issue is in merge handling inside lib/loader.js:

• storeMappingPair(...) iterates every element of a merge sequence when key tag is tag:yaml.org,2002:merge.
• For each element, it calls mergeMappings(...).
• mergeMappings(...) computes Object.keys(source) and performs _hasOwnProperty.call(destination, key) checks for each key.

When input is of the form:

a: &a {k0:0, k1:0, ..., kK:0}
b: {<<: [*a, *a, *a, ... repeated M times ...]}
all *a entries refer to the same anchored object. After the first merge, subsequent merges are semantically no-ops, but the parser still reprocesses all keys each time.
Resulting work is O(K * M), while input size is O(K + M), giving quadratic scaling as payload grows.
Relevant code path:
lib/loader.js in storeMappingPair(...) merge branch (keyTag === 'tag:yaml.org,2002:merge')
lib/loader.js mergeMappings(...)

Root cause

File: lib/loader.js
Function: storeMappingPair(state, _result, overridableKeys, keyTag, keyNode,
valueNode, startLine, startLineStart, startPos)
Lines: ~359-366

if (keyTag === 'tag:yaml.org,2002:merge') {
  if (Array.isArray(valueNode)) {
    for (index = 0, quantity = valueNode.length; index < quantity; index += 1) {
      mergeMappings(state, _result, valueNode[index], overridableKeys);
    }
  } else {
    mergeMappings(state, _result, valueNode, overridableKeys);
  }
}

When the merge value is a sequence (YAML 1.1 <<: [ *a, *a, ... ]), each element
is handed to mergeMappings() without deduplication. mergeMappings() then does

sourceKeys = Object.keys(source);
for (index = 0; index < sourceKeys.length; index += 1) {
  key = sourceKeys[index];
  if (!_hasOwnProperty.call(destination, key)) {
    setProperty(destination, key, source[key]);
    overridableKeys[key] = true;
  }
}

Every alias reference in the sequence resolves (by design) to the SAME object
via state.anchorMap. After the first merge, every subsequent merge of that same
reference is a pure no-op semantically, but still performs:

• one Object.keys(source) call (O(K))
• K _hasOwnProperty.call checks on the destination

Total: M * K hasOwnProperty checks + M Object.keys allocations, while the final
object and all observable side effects are identical to a single merge.

YAML semantics for <<: are idempotent and commutative over duplicate sources,
so collapsing duplicates preserves behavior exactly; this isn't a spec trade-off.

PoC

Environment:
js-yaml version: 4.1.1
Node.js: v24.5.0
Platform: arm64 macOS (reproduced consistently)
Reproduction script:
Create many keys in one anchored map (&a).
Merge that same alias repeatedly via <<: [*a, *a, ...].
Measure parse time and compare with control payload using single merge (<<: *a).
Observed repeated runs (same machine):
K=M=1000, input 9,909 bytes: ~33–36 ms
K=M=2000, input 20,909 bytes: ~121–123 ms
K=M=4000, input 42,909 bytes: ~524–537 ms
K=M=6000, input 64,909 bytes: ~1,608–1,829 ms
K=M=8000, input 86,909 bytes: ~3,395–3,565 ms
Control (single merge, similar key counts):
K=2000: ~1–2 ms
K=4000: ~3 ms
K=8000: ~5 ms
Also verified: repeated-merge output equals single-merge output (same key count and same JSON), confirming excess time is redundant computation.

Impact

This is a denial-of-service vulnerability (CPU exhaustion / algorithmic complexity).
Any service parsing untrusted YAML with js-yaml can be impacted, including API backends, CI tools, config processors, and automation services. An attacker can submit crafted YAML to significantly increase CPU time and reduce availability.

Suggested fix:

Dedupe the merge source list by reference before invoking mergeMappings. Any of
the following are minimal and preserve YAML 1.1 merge semantics:

dedupe in storeMappingPair:

if (keyTag === 'tag:yaml.org,2002:merge') {
  if (Array.isArray(valueNode)) {
    var seen = new Set();
    for (index = 0, quantity = valueNode.length; index < quantity; index += 1) {
      var src = valueNode[index];
      if (seen.has(src)) continue;   // idempotent; skip redundant alias
      seen.add(src);
      mergeMappings(state, _result, src, overridableKeys);
    }
  } else {
    mergeMappings(state, _result, valueNode, overridableKeys);
  }
}</alert_description>

moderate</s...

• Resolves github/copilot-survey-engine alert fix: upgrade js-yaml to 3.15.0 (CVE-2026-53550) #56

[Copilot]

Pull request overview

Pins the transitive js-yaml dependency to the patched version addressing CVE-2026-53550.

Changes:

• Adds a js-yaml@3.15.0 npm override.
• Updates the lockfile resolution and integrity hash.

Show a summary per file

File	Description
package.json	Pins the patched transitive dependency.
package-lock.json	Locks js-yaml to version 3.15.0.

Review details

Tip

Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

• Files reviewed: 1/2 changed files
• Comments generated: 0
• Review effort level: Medium