Back to skill

Security audit

受限资产·抵押质押冻结逐项登记与可动用资金缺口

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marks this skill suspicious with medium confidence because scanners report undeclared MCP discovery, credential and document transmission risks, and a validation weakness; analysis was partial.

Consider the reported undeclared MCP activity, endpoint credential handling, and external processing of supplied documents before installing. The scanner also reports that the amount-to-quotation comparison described by the skill is missing. Coverage is incomplete: three of four components were fully inspected, and the fixture runner was partially inspected, so the results do not establish that unreported behavior 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
  • 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 (7)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The supplied chunk performs network-based MCP discovery and authenticated tool enumeration, neither of which is described in the declared purpose. It contains no report parsing, source anchoring, restricted-asset registration, or arithmetic validation. Such discovery could support a larger workflow, but this chunk does not establish any connection to the declared financial-disclosure task. The destination of the authenticated request depends on MCP_ENDPOINT; the code alone does not establish credential theft or other 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 137)May include surrounding context.

md
| `scripts/fixtures/run_fixtures.sh` | 离线样例 runner:自测→好样→坏样三档,坏样注入必先断言落地;期望退码由自测末行的「不可判=N」现算,不写死 |

External Transmission

Medium
Category
Data Exfiltration
Confidence
88% confidence
Finding

Fetching a public catalog is not itself data exfiltration, but the associated command sends CUE_API_KEY to MCP_ENDPOINT without checking its scheme or destination. If that endpoint is misconfigured or populated from compromised routing metadata, the bearer credential could be disclosed to an unauthorized host or transmitted without TLS.

Content

Scanner excerpt · README.md (reported line 111)May include surrounding context.

bash
  # ① 匿名取域清单与 routing
  curl -sS https://cuecue.cn/api/mcp-catalog -o /tmp/mcp-catalog.json
  python3 -c "import json;d=json.load(open('/tmp/mcp-catalog.json'));print(d)"

  # ② 带凭据握手取工具表

The workflow directs screenshots and scanned documents to an external reader without a privacy warning.

Medium
Category
Output Handling
Confidence
93% confidence
Finding

The workflow directs user-supplied screenshots and scans to an external reader without a sensitivity check or explicit disclosure of document transmission. Annual reports are normally public, which reduces the risk, but supplied files may contain private annotations or unrelated confidential pages.

Content

No source excerpt is available for this finding.

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

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 directs screenshots and scanned documents to an external reader service without warning that document contents will be transmitted.

Medium
Category
Output Handling
Confidence
91% confidence
Finding

The skill tells the agent to send screenshots and scans to an external reader without explicitly describing the transfer or checking whether the supplied content is sensitive. Public financial disclosures are low-sensitivity inputs, but user-provided copies may include confidential additions that should not automatically leave the user's environment.

Content

No source excerpt is available for this finding.

L156–L157 claim RA-SUM/RA-RATIO check agreement between registered numbers and quoted numbers, but neither check does so.

Medium
Category
Excessive Agency
Confidence
98% confidence
Finding

The documentation assigns agreement between registered values and quoted values to RA-SUM and RA-RATIO, but both checks operate on text before the quotation and never compare the two. Incorrect or deliberately altered registered amounts can therefore retain plausible quotations and pass validation if their internal totals and ratios remain consistent, undermining the register's claimed source fidelity.

Content

No source excerpt is available for this finding.