Back to skill

Security audit

股权激励查询

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marked this skill suspicious because scanners report that it sends a user's question to a remote rewrite service before asking about privacy and includes functionality and workflow requirements beyond equity incentive analysis.

Consider the reported privacy and purpose concerns before installing. In particular, check whether sending questions to the remote rewrite service and including individual wealth-prospecting features fit your needs. The scan is incomplete, so these results do not establish that the skill is safe.

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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (7)

External Script Fetching

High
Category
Supply Chain
Confidence
90% confidence
Finding

Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.

Content

Scanner excerpt · SKILL.md (reported line 493)May include surrounding context.

md
CUE_KEY=$(python3 -c "import json;print(json.load(open('$HOME/.cue/config.json'))['api_key'])" 2>/dev/null || echo "$CUE_API_KEY")
echo "=== 1/4 API Key ===" && [ -n "$CUE_KEY" ] && echo "已配置" || echo "未配置!"
echo "=== 2/4 Cue 服务 ===" && curl -sS --max-time 10 "https://cuecue.cn/api/health" -H "Authorization: Bearer $CUE_KEY"
echo "=== 3/4 搭子 ===" && curl -sS --max-time 10 "https://cuecue.cn/api/playbook" -H "Authorization: Bearer $CUE_KEY" | python3 -c "import sys,json;scenes=json.load(sys.stdin).get('data',{}).get('scenes',[]);buddy=[b for s in scenes if s.get('secondary_category')=='资本运作' for b in s.get('buddies',[]) if b.get('title')=='股权激励查询'];print(f'可用:{len(buddy)}个') if buddy else print('暂不可用')"
echo "=== 4/4 剩余积分 ===" && python3 -c "
import json, urllib.request, os
p = os.path.expanduser('~/.cue/config.json')

Mandatory verbatim Chinese prompts impose an output language without user choice.

Medium
Category
Output Handling
Confidence
88% confidence
Finding

The skill requires the Chinese title and options to be used verbatim, explicitly prohibiting changes. This forces that portion of the response into Chinese regardless of the user's language, without offering a language choice or documenting a justification for the restriction.

Content

No source excerpt is available for this finding.

The skill exposes individual wealth-prospecting functionality beyond company incentive-plan analysis.

Medium
Category
Excessive Agency
Confidence
94% confidence
Finding

L339 explicitly describes a tool for finding recently awarded high-net-worth individuals, filtered by market value and region, for wealth-adviser customer acquisition; L360 provides an invocation example. This repurposes equity-incentive disclosures into personal sales-prospect lists, rather than the company-plan querying, benchmarking, and evaluation described in the manifest.

Content

No source excerpt is available for this finding.

The raw user question is sent to the rewrite API before any privacy warning or user confirmation.

Medium
Category
Output Handling
Confidence
97% confidence
Finding

The freeform workflow passes the original user question to the remote rewrite API before presenting its privacy-related confirmation. If that question contains confidential business information or personal data, server-side masking happens only after disclosure to Cue; the later confirmation cannot authorize or prevent that initial transmission.

Content

No source excerpt is available for this finding.

Sudo/Root Execution

Medium
Category
Privilege Escalation
Confidence
70% confidence
Finding

Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.

Content

Scanner excerpt · SKILL.md (reported line 461)May include surrounding context.

md
| 目标格式 | 依赖 | macOS | Ubuntu |
|----------|------|-------|--------|
| Word (.docx) | pandoc | `brew install pandoc` | `sudo apt install pandoc` |
| PDF (.pdf) | pandoc + LaTeX | `brew install --cask basictex` | `sudo apt install texlive-xetex` |

---

Sudo/Root Execution

Medium
Category
Privilege Escalation
Confidence
70% confidence
Finding

Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.

Content

Scanner excerpt · SKILL.md (reported line 462)May include surrounding context.

md
| 目标格式 | 依赖 | macOS | Ubuntu |
|----------|------|-------|--------|
| Word (.docx) | pandoc | `brew install pandoc` | `sudo apt install pandoc` |
| PDF (.pdf) | pandoc + LaTeX | `brew install --cask basictex` | `sudo apt install texlive-xetex` |

---

The skill mandates referral and social-media promotion after otherwise successful analytical tasks.

Low
Category
Excessive Agency
Confidence
90% confidence
Finding

The low-balance workflow mandates promotional content and explicitly prevents other follow-up questions until its own prompt has been delivered. This is a limited workflow-integrity issue: provider marketing can displace the user's analytical workflow, although the skill does not automatically purchase credits, send invitations, or publish reports.

Content

No source excerpt is available for this finding.