Back to skill

Security audit

token-manager

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this skill suspicious because it reports that token estimation may send supplied text to an external API despite local-only assurances; confidence is medium, and inspection of the scripts was incomplete.

Consider the privacy and billing implications before installing. The scanners report that supplied text may be transmitted to an external provider, and they did not fully inspect three of the four components. Review the skill's data handling and provider choices before using it with sensitive text or credentials.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (19)

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 41)May include surrounding context.

md
node scripts/manager.js report \

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 48)May include surrounding context.

md
node scripts/manager.js balance deepseek

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 51)May include surrounding context.

md
node scripts/manager.js tokens moonshot "要估算的文本"

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 52)May include surrounding context.

md
node scripts/manager.js tokens moonshot '[{"role":"user","content":"..."}]' --model kimi-k3.1-pro

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 55)May include surrounding context.

md
node scripts/manager.js estimate deepseek 1000000 300000 deepseek-flash

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 58)May include surrounding context.

md
node scripts/manager.js providers # 列出支持的 provider

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 59)May include surrounding context.

md
node scripts/manager.js set-provider deepseek

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 60)May include surrounding context.

md
node scripts/manager.js history # 查看使用历史

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 134)May include surrounding context.

md
DeepSeek 峰值时段为北京时间工作日 9-12/14-18 点,其余时段约半价,上表按峰值计。价格会过时,更新方式:编辑 `scripts/manager.js` 中 `DEFAULT_CONFIG.providers.<id>.pricing`,或改本地覆盖文件 `.data/config.json`(不改默认

External Model or Provider Selection

High
Category
Excessive Agency
Confidence
90% confidence
Finding

Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.

Content

Scanner excerpt · SKILL.md (reported line 45)May include surrounding context.

md
--tokens-in 11000 --tokens-out 146 \
  --context-used 42000 --context-max 200000 \
  --thinking off \
  --provider moonshot --model kimi-k3.1-pro

# 查询余额
node scripts/manager.js balance deepseek

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 70)May include surrounding context.

md
node scripts/scheduler.js check moonshot 5 # 余额低于 ¥5 时告警(默认阈值 5)

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 71)May include surrounding context.

md
node scripts/scheduler.js stats # 告警历史统计

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 79)May include surrounding context.

md
node scripts/session-tracker.js record moonshot kimi-k3.1-pro 11000 146 0.15 CNY

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 80)May include surrounding context.

md
node scripts/session-tracker.js daily # 今日报告

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 81)May include surrounding context.

md
node scripts/session-tracker.js weekly # 近 7 天报告 + 趋势

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 82)May include surrounding context.

md
node scripts/session-tracker.js recommend # 省钱建议

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 96)May include surrounding context.

md
node scripts/session-tracker.js record "$PROVIDER" "$MODEL" "$TOKENS_IN" "$TOKENS_OUT" "$COST" "$CURRENCY"

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: env.

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

Token estimation uploads supplied text despite the documented local-only data guarantee.

Medium
Category
Excessive Agency
Confidence
96% confidence
Finding

Moonshot token estimation automatically sends the supplied text or message array to an external API when a key is available, including one obtained from the environment. Although official API estimation is mentioned elsewhere, blanket local-only and no-upload assurances can cause users or agents to submit sensitive content under an incorrect privacy assumption; an official provider is still an external recipient.

Content

No source excerpt is available for this finding.