Back to skill

Security audit

Spark Context Monitor

Security checks for vulnerabilities and agentic risk

Overview

This skill appears to only estimate and report the current chat's token usage locally, with no evidence of upload, persistence, or unsafe commands.

Reasonable to install if you are comfortable with a skill reading the current conversation history to compute aggregate token counts. Review the broad triggers and Chinese-only output, and update the dev dependency lockfile before using the package in a build or CI pipeline.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (18)

Known Vulnerable Dependency: brace-expansion==1.1.13 — 3 advisory(ies): CVE-2026-13149 (brace-expansion: DoS via exponential-time expansion of consecutive non-expanding); CVE-2026-14257 (brace-expansion: DoS via unbounded expansion length causing an out-of-memory pro); CVE-2026-69152 (brace-expansion: DoS via unbounded intermediate arrays, bypassing the CVE-2026-1)

High
Category
Supply Chain
Confidence
96% confidence
Finding

brace-expansion==1.1.13 is present and is associated with multiple denial-of-service issues involving pathological expansion causing extreme CPU or memory consumption. Even though it is transitive and primarily used by development tooling, these parser-style DoS flaws can be triggered by attacker-controlled patterns if any tooling consumes untrusted glob-like input.

Content

No source excerpt is available for this finding.

Known Vulnerable Dependency: browserslist==4.28.2 — 2 advisory(ies): CVE-2026-73088 (Browserslist: Uncaught crash / prototype write via untrusted browserslist-stats.); CVE-2026-73089 (Browserslist: Unbounded memory growth (no cache eviction) via distinct query res)

High
Category
Supply Chain
Confidence
91% confidence
Finding

browserslist==4.28.2 matches the advisory and the issues include crash/prototype-write and unbounded memory growth from untrusted query/stat inputs. In this skill, browserslist is a dev-time dependency rather than production logic, which lowers exposure, but CI or local tooling that ingests attacker-influenced configuration could still be disrupted.

Content

No source excerpt is available for this finding.

Known Vulnerable Dependency: js-yaml==3.14.2 — 4 advisory(ies): CVE-2026-84375 (js-yaml: maxTotalMergeKeys does not limit CPU use for empty merge sources); CVE-2026-59869 (js-yaml: YAML merge-key chains can force quadratic CPU consumption); GHSA-5p4m-2wfm-xmqj (JS-YAML: Quadratic CPU consumption in !!omap resolution (3.x and 4.x) — CVE-2026) +1 more

High
Category
Supply Chain
Confidence
97% confidence
Finding

js-yaml==3.14.2 is present and the reported advisories concern quadratic or otherwise excessive CPU consumption during YAML parsing. Because YAML parsers are commonly exposed to attacker-controlled configuration or fixture files, this can become a practical denial-of-service vector even in development and test pipelines.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The title and the entire user-facing documentation are written in Chinese, and the example natural-language triggers are also Chinese-centric except for a single English phrase. There is no indication that the skill is region-specific or that users can opt into another language, which may violate a language/locale policy requiring user choice.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill description is presented entirely in Chinese from the title onward, with no indication that users may choose another language or that the Chinese-only presentation is region-specific. Under the policy, forcing a specific language without opt-in is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The trigger phrase at line 54 ("token 使用情况") is broad enough that it could plausibly appear in ordinary user conversation, increasing the chance of accidental skill activation. Even for a read-only monitoring skill, unintended invocation can leak contextual metadata about the current session or disrupt expected agent behavior.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The trigger phrase at line 56 ("查看 token") is vague and conversational, which weakens activation control and makes false-positive triggering more likely. In an agent ecosystem, imprecise triggers can cause the wrong skill to run when the user is merely discussing token usage rather than intentionally invoking the tool.

Content

No source excerpt is available for this finding.

Known Vulnerable Dependency: @babel/core==7.29.0 — 1 advisory(ies): CVE-2026-49356 (@babel/core: Arbitrary File Read via sourceMappingURL Comment)

Low
Category
Supply Chain
Confidence
93% confidence
Finding

The lockfile pins @babel/core to 7.29.0, and the reported advisory affects that exact version. In this skill context it is only a dev dependency used in the Jest/TypeScript toolchain, so exploitation would likely require processing attacker-controlled source content during build or test, which reduces but does not eliminate risk.

Content

No source excerpt is available for this finding.

Known Vulnerable Dependency: baseline-browser-mapping==2.10.15 — 1 advisory(ies): CVE-2026-45819 (baseline-browser-mapping process termination on invalid input causes denial of s)

Low
Category
Supply Chain
Confidence
85% confidence
Finding

baseline-browser-mapping==2.10.15 is flagged for a denial-of-service condition on invalid input, and the exact vulnerable version is present. In this repository it appears only as a transitive dev dependency of browserslist, so the practical exposure is limited to local/CI tooling rather than runtime skill behavior.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The natural-language description includes Chinese text ("上下文使用率查询") with no indication that the skill supports multiple languages or that the locale is intentionally restricted. This can create a language/locale policy issue if users are not given a choice or informed of the constraint.

Content

No source excerpt is available for this finding.

Unpinned Dependencies

Low
Category
Supply Chain
Confidence
40% confidence
Finding

Dependencies lack version pinning, allowing potential malicious package updates. Consider pinning versions.

Content

Scanner excerpt · package.json (reported line 19)May include surrounding context.

json
"author": "Spark",
  "license": "MIT",
  "devDependencies": {
    "@types/jest": "^29.5.14",
    "@types/node": "^20.19.39",
    "jest": "^29.7.0",
    "ts-jest": "^29.4.9",

Unpinned Dependencies

Low
Category
Supply Chain
Confidence
40% confidence
Finding

Dependencies lack version pinning, allowing potential malicious package updates. Consider pinning versions.

Content

Scanner excerpt · package.json (reported line 20)May include surrounding context.

json
"license": "MIT",
  "devDependencies": {
    "@types/jest": "^29.5.14",
    "@types/node": "^20.19.39",
    "jest": "^29.7.0",
    "ts-jest": "^29.4.9",
    "typescript": "^5.9.3"

Unpinned Dependencies

Low
Category
Supply Chain
Confidence
40% confidence
Finding

Dependencies lack version pinning, allowing potential malicious package updates. Consider pinning versions.

Content

Scanner excerpt · package.json (reported line 21)May include surrounding context.

json
"devDependencies": {
    "@types/jest": "^29.5.14",
    "@types/node": "^20.19.39",
    "jest": "^29.7.0",
    "ts-jest": "^29.4.9",
    "typescript": "^5.9.3"
  }

Unpinned Dependencies

Low
Category
Supply Chain
Confidence
40% confidence
Finding

Dependencies lack version pinning, allowing potential malicious package updates. Consider pinning versions.

Content

Scanner excerpt · package.json (reported line 22)May include surrounding context.

json
"@types/jest": "^29.5.14",
    "@types/node": "^20.19.39",
    "jest": "^29.7.0",
    "ts-jest": "^29.4.9",
    "typescript": "^5.9.3"
  }
}

Unpinned Dependencies

Low
Category
Supply Chain
Confidence
40% confidence
Finding

Dependencies lack version pinning, allowing potential malicious package updates. Consider pinning versions.

Content

Scanner excerpt · package.json (reported line 23)May include surrounding context.

json
"@types/node": "^20.19.39",
    "jest": "^29.7.0",
    "ts-jest": "^29.4.9",
    "typescript": "^5.9.3"
  }
}

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

The manifest presents the skill description, category, tags, features, and triggers entirely in Chinese, with no indication that users can opt into another language or that the skill is intentionally limited to a Chinese-speaking audience. This can violate language/locale policy when a skill implicitly assumes one language without user choice or explicit justification.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
93% confidence
Finding

The file’s natural-language description, trigger examples, and user-facing responses are primarily fixed in Chinese, which can force a specific language experience on users. Under the policy, locale or language constraints should either be optional for the user or clearly justified as region-specific.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

This TypeScript test file contains natural-language expectations showing the skill matches Chinese trigger phrases and English trigger phrases, while other assertions elsewhere in the file expect Chinese status labels such as '正常', '警告', and '严重'. Because there is no indication in this file of user opt-in or configurable language selection, the skill appears to enforce a locale-specific response behavior.

Content

No source excerpt is available for this finding.