Back to skill

Security audit

clawec-shopee-item-search

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed ClawEC Shopee search helper that sends user-chosen query parameters to ClawEC using the user's API key.

Install this only if you trust ClawEC with your Shopee search parameters and CLAWEC_API_KEY. Do not provide unrelated secrets; the reviewed artifact shows no local file harvesting, persistence, or hidden execution.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (7)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
93% confidence
Finding

The skill includes executable shell usage (curl, bash scripts/query.sh) but does not declare any tool scope or allowed-tools restrictions. This can lead to overbroad execution privileges at runtime, making it easier for an agent to invoke shell unexpectedly or in environments where shell access should be constrained.

Content

No source excerpt is available for this finding.

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.

调用

bash
curl -s -X POST "https://www.clawec.com/api/aigc/ec/shopee/data/item/search" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $CLAWEC_API_KEY" \
  -d '{"site":"tw","categoryId":100630,"sortType":1,"sortOrder":"desc","pageNo":1,"pageSize":10}'

External Transmission

Medium
Category
Data Exfiltration
Confidence
70% 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 · scripts/query.sh (reported line 34)May include surrounding context.

sh
print(json.dumps(body, ensure_ascii=False))
' "$SITE" "$CATEGORY_ID" "$SORT_TYPE" "$SORT_ORDER" "$PAGE_NO" "$PAGE_SIZE" "$TIMEST" "$FILTERS_JSON")

curl -s -X POST "https://www.clawec.com/api/aigc/ec/shopee/data/item/search" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $API_KEY" \
  -d "$PAYLOAD"

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

This shell script performs a network POST request to an external service and includes both user-provided payload data and an authorization bearer token, but the file contains no comment, print/log message, or confirmation disclosing that data is being transmitted. For code files, outbound network calls that transmit user or system data should have some visible warning unless the disclosure is otherwise documented in the skill description.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

The documentation states '默认中文报告', which imposes a specific output language by default. Under the policy, locale or language constraints should either be opt-in or clearly justified; this file does not offer a user choice or justify why Chinese is required.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

This markdown file presents all operational instructions and schema descriptions exclusively in Chinese. Under the policy, forcing a specific language without user opt-in can be a natural-language policy violation unless the locale restriction is explicitly justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

The usage and environment-variable error messages are hardcoded in Chinese, which imposes a specific language on users without any opt-in or documented regional justification. This matches the policy concern for language or locale restrictions in natural-language content.

Content

No source excerpt is available for this finding.