Back to skill

Security audit

爆款内容调研 okdata

Security checks for vulnerabilities and agentic risk

Overview

ClawScan’s verdict is benign: scanners found no AIG issues, while Skillspector flagged an API request and a mismatch between the stated research purpose and a Weibo trends request; coverage was partial.

The verdict is benign, but review whether the Weibo trends request fits what you want this skill to do and whether you trust the okdata API before providing its key. Skillspector inspected the listed component but reported partial analysis because many local references could not be resolved, so the evidence is incomplete.

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 Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The request targets /v1/weibo/trends/list without any topic parameter. Weibo is a distinct, undeclared platform, not WeChat Official Accounts. The supplied chunk also contains no post searching, engagement ranking, full-post retrieval, or content-pattern analysis. Authentication and request headers are ordinary implementation details, not separate mismatches.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% 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 139)May include surrounding context.

go in the query string, and the key comes from the environment, never from the chat:

bash
curl -sG "https://api.okdata.online/v1/weibo/trends/list" \
  -H "Authorization: Bearer $OKDATA_API_KEY" \
  -H "Idempotency-Key: $(uuidgen)" \
  --data-urlencode "view=compact"