Back to skill

Security audit

clawec-tiktok-category-opportunity

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed ClawEC API helper for TikTok category research, with expected outbound API use and no hidden persistence or destructive behavior.

Install only if you are comfortable sending search keywords, selected TikTok region, table preference, and your ClawEC bearer token to clawec.com. Use a dedicated API key with normal rotation practices, avoid putting sensitive private data in keywords, and review API costs or point usage before enabling table output.

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
84% confidence
Finding

The skill documents shell-based execution paths (curl and bash scripts/analyze.sh) but does not declare any tool scope such as permissions or allowed-tools. This creates an authorization gap where an agent may invoke shell/network capabilities more broadly than intended, increasing the chance of unintended command execution or data egress during use.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
92% confidence
Finding

The skill instructs sending user-supplied keywords and an authorization bearer token to an external third-party API endpoint. External transmission is expected for this skill's purpose, but it still creates a real data egress and credential-handling risk, especially if users are not clearly informed or if sensitive inputs are sent without minimization.

Content

Scanner excerpt · SKILL.md (reported line 60)May include surrounding context.

调用

bash
curl -s -X POST "https://www.clawec.com/api/aigc/ec/product_search_v2" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $CLAWEC_API_KEY" \
  -d '{"keyword":"wireless earbuds","target_platform":"tiktok","region":"ID","table":0}'

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The instructions explicitly require the skill to '输出中文机会分析报告' and describe the output as '默认中文报告' without indicating that the user may choose another language. This is a natural-language locale policy issue because it imposes a specific language by default rather than offering opt-in or adaptation to user preference.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

Line L72 instructs that fields with UP/DOWN prefixes should be translated into Chinese, which imposes a specific language behavior. Under the policy, forcing a language without user opt-in is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The script defaults REGION to "ID" when the user does not supply a region, which imposes a locale-specific behavior automatically. There is no accompanying natural-language explanation, opt-in, or indication that this regional default is required for a justified region-specific use case.

Content

No source excerpt is available for this finding.

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/analyze.sh (reported line 16)May include surrounding context.

sh
"table": int(sys.argv[3]),
}))' "$KEYWORD" "$REGION" "$TABLE")

curl -s -X POST "https://www.clawec.com/api/aigc/ec/product_search_v2" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $API_KEY" \
  -d "$PAYLOAD"

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The script performs an HTTP POST to an external service, transmitting the user-provided keyword, region, table selection, and an authorization bearer token. There is no confirmation prompt, logging, comment, or docstring disclosing this outbound data transmission to the user within the file.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.