ClawHub
Back to skill

Security audit

clawec-amazon-category-opportunity

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed ClawEC API wrapper for Amazon keyword opportunity analysis, with expected external API use and no persistence or destructive behavior.

Install only if you are comfortable sending your search keywords, Amazon region, table option, and ClawEC bearer token to clawec.com. Use a dedicated ClawEC API key, avoid confidential product terms if that matters to you, and prefer reviewing the curl command before running the helper script.

A.I.G

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

SkillSpector

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 (8)

Lp3

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding
The skill instructs use of shell commands and a local script, but it does not declare any explicit tool scope or allowed-tools boundary. That increases risk because an agent may execute shell-capable behavior more broadly than intended, including handling secrets and network access without clear confinement.

External Transmission

Medium
Category
Data Exfiltration
Content
## 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":"amazon","region":"US","table":0}'
Confidence
88% confidence
Finding
The skill sends user-provided keywords and an authorization bearer token to an external third-party API. External transmission is expected for this skill’s purpose, but it still creates real data-handling and secret-exposure risk if users are not informed, if sensitive inputs are passed through, or if logs/telemetry capture the Authorization header.

External Transmission

Medium
Category
Data Exfiltration
Content
"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"
Confidence
70% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The script sends the provided keyword, region, table value, and a bearer token to an external HTTPS API via curl, but it provides no confirmation prompt, log message, or explanatory comment/docstring warning the user that data will be transmitted off-system. For a code file, this matches missing disclosure for network/HTTP calls that transmit user or system data.

Natural-Language Policy Violations

Low
Confidence
94% confidence
Finding
The instructions say to '输出中文机会分析报告' and '默认中文报告', which imposes a language choice in the skill's behavior. The policy allows locale constraints only when the skill offers opt-in or clearly justifies the restriction; neither is stated here.

Natural-Language Policy Violations

Low
Confidence
81% confidence
Finding
Line L16 states that `target_platform` is fixed to `amazon`, which is a natural-language constraint embedded in the specification. While this is not a language restriction, it is a hard policy-like limitation presented without any user choice mechanism or justification elsewhere in the document.

Natural-Language Policy Violations

Low
Confidence
89% confidence
Finding
The only user-facing strings in the script are Chinese messages for usage and missing environment variable handling, with no opt-in or indication that the tool is intentionally locale-specific. This is a natural-language locale policy concern because the script imposes a language choice on users without offering alternatives.

Missing User Warnings

Low
Confidence
86% confidence
Finding
The script reads CLAWEC_API_KEY from the environment and later uses it for an outbound request, but there is no comment, docstring, or user-facing notice explaining that a credential will be consumed. This is a safety-relevant credential access pattern lacking disclosure under the code-file criteria.

Static analysis

No suspicious patterns detected.