Back to skill

Security audit

股权质押与解押跟踪·逐条挂源

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marks this skill suspicious because scanners report behavior and privacy concerns that do not clearly fit its pledge-tracking purpose; one referenced script received only partial analysis.

Consider whether the reported external parsing and MCP discovery are necessary for your use, and avoid providing private URLs or local paths unless you are comfortable with their disclosure. Treat the checker’s percentage validation as a concern. Analysis was partial for one referenced script, so the evidence is incomplete; the suspicious verdict does not establish malicious intent.

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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • 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 (12)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
94% confidence
Finding

The supplied chunk performs service discovery rather than retrieving or processing pledge announcements, linking transactions, or calculating disclosed balance changes. Such discovery could support the declared workflow, but the supplied code establishes no connection between the catalog or listed tools and that workflow. It also does not extract or assign MCP_ENDPOINT, despite the comment suggesting endpoint discovery. No data exfiltration or invocation of the discovered tools is shown.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
90% confidence
Finding

The supplied chunk performs MCP service discovery and tool enumeration, not the declared announcement-tracking workflow. Such calls could be supporting setup if linked to a relevant disclosure source, but the supplied code establishes no such connection and contains no pledge-specific retrieval, extraction, citation, or balance tracking. This assessment is limited to the supplied chunk; it does not establish malicious intent.

Content

No source excerpt is available for this finding.

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 131)May include surrounding context.

md
bash scripts/fixtures/run_fixtures.sh # 离线样例三档(零网络零计费)

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

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

curl -s https://cuecue.cn/api/mcp-catalog | head -c 500

2) MCP handshake, confirm the three tools are present

curl -s -X POST "$MCP_ENDPOINT" -H 'Content-Type: application/json'
-d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'

text

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

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

curl -s https://cuecue.cn/api/mcp-catalog | head -c 500

2) 按 MCP 协议握手,确认三枚工具在场

curl -s -X POST "$MCP_ENDPOINT" -H 'Content-Type: application/json'
-d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'

text

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.en.md (reported line 91)May include surrounding context.

curl -s https://cuecue.cn/api/mcp-catalog | head -c 500

2) MCP handshake, confirm the three tools are present

curl -s -X POST "$MCP_ENDPOINT" -H 'Content-Type: application/json'
-d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'

text

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 99)May include surrounding context.

curl -s https://cuecue.cn/api/mcp-catalog | head -c 500

2) 按 MCP 协议握手,确认三枚工具在场

curl -s -X POST "$MCP_ENDPOINT" -H 'Content-Type: application/json'
-d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'

text

The output contract mandates Chinese text without offering a language choice.

Medium
Category
Output Handling
Confidence
92% confidence
Finding

The skill requires an exact Chinese declaration and prescribes Chinese section headings and labels in its output contract. It offers no language opt-in or localization choice, and the A-share subject matter alone does not establish a need to force Chinese output.

Content

No source excerpt is available for this finding.

The parsing workflow sends user-supplied announcement URLs or local paths to an external service without a privacy warning.

Medium
Category
Output Handling
Confidence
93% confidence
Finding

The workflow directs the agent to send user-provided URLs or local paths to an external parser without a sensitivity check or explicit approval of that disclosure. Although public announcements reduce the usual exposure, private URL tokens and local path names can still reveal sensitive information; the supplied text does not establish that file contents are uploaded.

Content

No source excerpt is available for this finding.

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

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.

The workflow sends announcement URLs or local file paths to an external parsing service without a privacy warning.

Medium
Category
Output Handling
Confidence
96% confidence
Finding

The instructions send announcement URLs or local paths to an external parsing channel without requiring informed approval or screening for sensitive inputs. Most announcements are public, but private URL parameters and local path metadata can disclose confidential information; actual file-content transfer is not demonstrated by this source.

Content

No source excerpt is available for this finding.

The documented prohibition on unsupported percentages is bypassed whenever a detail row contains a missing-data marker.

Medium
Category
Excessive Agency
Confidence
99% confidence
Finding

The percentage-validation loop skips an entire detail row whenever its body contains 未取到 or 未检索到, even if the same row also asserts unsupported percentages. An adversarial card can exploit this exemption, reconcile the missing-row count, and receive PASS despite violating the financial-data integrity rule; PASS still does not independently verify source truth.

Content

No source excerpt is available for this finding.