Back to skill

Security audit

行业景气与竞争格局研判

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marks this skill suspicious because scanners report exposed API-key handling, an unpinned external runner, and behavior that does not fully match its stated industry-research purpose; coverage is incomplete.

Consider the verdict’s credential and supply-chain concerns before installing. Do not paste a reusable API key into chat; use a protected local credential method if available. Skillspector scanned the one reported Markdown component, but overall analysis was marked partial because a local path reference was missing, so evidence is incomplete. The separate AIG scan completed with no findings, which does not resolve that coverage gap.

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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Findings (8)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The supplied commands only convert an existing report into other formats. They do not invoke Cue, gather industry information, assess competitive dynamics, or identify investment opportunities. Document export could support a broader research workflow, but the supplied chunk contains only that conversion functionality and does not implement the declared primary purpose.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
92% confidence
Finding

Installing a research runner is consistent with the skill's purpose, so the description mismatch alone is not a vulnerability. However, the workflow clones or automatically updates an unpinned external repository and subsequently executes its Python code with the agent's permissions and access to Cue credentials; a compromised upstream repository could therefore cause local code execution and credential theft.

Content

No source excerpt is available for this finding.

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 235)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')=='行业研究' for b in s.get('buddies',[]) if b.get('title')=='行业景气与竞争格局研判'];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')

The setup workflow requests an API key in chat without warning about credential exposure.

Medium
Category
Output Handling
Confidence
99% confidence
Finding

The setup explicitly asks users to paste a live API key into the agent conversation, exposing it to conversation storage, logging, and any systems processing that conversation. Repeated claims that the agent cannot view the key do not mitigate this exposure and conflict with the requested handling.

Content

No source excerpt is available for this finding.

The onboarding instructions require users to disclose their API key in the agent conversation.

Medium
Category
Data Exfiltration
Confidence
99% confidence
Finding

Requiring API-key disclosure in chat unnecessarily expands access to a reusable authentication secret and may permit unauthorized Cue usage or credit consumption if the conversation is exposed. This is the same underlying credential-handling issue as finding-e86186072a854e949dd8be71463e329b, not an independent exploit.

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 210)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 211)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 research workflow mandates referral and social-sharing promotions beyond the manifest's industry-analysis purpose.

Low
Category
Excessive Agency
Confidence
92% confidence
Finding

The manifest promises industry-cycle and competitive-landscape research, but L114–L139 require a post-delivery promotional interaction whenever the remaining balance is below 100, including referral recruitment and sharing on Xiaohongshu for rewards. Explaining insufficient credits is a reasonable service dependency; mandating these growth activities after successful delivery, including constructing a promotional link containing the report ID, goes beyond that dependency and the stated research purpose. The workflow does not automatically publish the report, but it makes unrelated promotion a required part of completion.

Content

No source excerpt is available for this finding.