Back to skill

Security audit

clawec-ozon-product-detail

Security checks for vulnerabilities and agentic risk

Overview

This skill is a narrow, disclosed Ozon product-detail lookup that sends user-supplied product IDs to the ClawEC API using a user-provided API key.

Install this only if you are comfortable sending the queried Ozon item IDs and your ClawEC API credential to clawec.com. Keep the API key in an environment variable or secret store, avoid pasting it into shared logs or chats, and review product IDs before running batch queries.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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
89% confidence
Finding

The skill includes shell-based execution examples and an explicit script invocation, but it does not declare any tool scope or allowed-tools restrictions. That increases the chance an agent may execute shell/network actions without clear sandboxing or least-privilege controls, which is risky for a skill that sends user-supplied identifiers and bearer-authenticated requests to an external API.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
86% confidence
Finding

The skill instructs the agent to transmit data and an authorization bearer token to an external third-party service. External transmission is expected for an API-integration skill, but it remains security-relevant because user-provided item IDs and potentially sensitive business-query patterns are sent off-platform, and the skill provides shell commands that could expose the token through unsafe execution environments, logs, or process history.

Content

Scanner excerpt · SKILL.md (reported line 43)May include surrounding context.

单个商品:

bash
curl -s -X POST "https://www.clawec.com/api/aigc/ec/ozon/data/product/detail" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $CLAWEC_API_KEY" \
  -d '{"itemIds":"123456789","period":"TWENTY_EIGHT_DAY"}'

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 31)May include surrounding context.

sh
print(json.dumps(body))
' "$ITEM_IDS" "$PERIOD" "$SORT_FIELD" "$SORT_DIRECTION" "$UPDATE_PERIOD")

curl -s -X POST "https://www.clawec.com/api/aigc/ec/ozon/data/product/detail" \
  -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

This shell script sends user-supplied item IDs to an external HTTPS endpoint and authenticates with a sensitive environment variable. There is no confirmation prompt, logging, comment, or other user-facing disclosure in the file warning that data will be transmitted off-system using the provided API key.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

The markdown states '默认中文报告', which sets a language preference for responses without indicating user opt-in or an available language choice. This is a natural-language policy concern because the skill appears to impose a locale/output language by default rather than adapting to the user's preference.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

Line L098 states that itemTitle is Russian and instructs implementers to preserve and display the original text. This is a natural-language locale constraint presented as a requirement, with no indication that users may choose another language or that the behavior is optional.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
97% confidence
Finding

The usage and error strings are written only in Chinese, which imposes a specific language on all users without opt-in or documented locale scope. This matches the policy concern for language or locale restrictions expressed in natural-language content within code.

Content

No source excerpt is available for this finding.