Back to skill

Security audit

抖音数据 API · Douyin data API · DataXAPI

Security checks for vulnerabilities and agentic risk

Overview

The scanners label this Douyin data lookup skill benign because its reported behavior appears purpose-aligned, while noting an unpinned install command and a privacy disclosure gap; confidence is medium and coverage is incomplete.

The verdict is benign, not risk-free. Before installing, consider whether you are comfortable sending Douyin search terms to DataXAPI, and avoid including private context. The installation commands do not pin a package version. Scanning was partial because local references could not be resolved, so the evidence does not establish that every referenced item was reviewed.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (5)

Endpoint discovery forwards the user's words to DataXAPI without a privacy warning.

Medium
Category
Output Handling
Confidence
90% confidence
Finding

The fallback workflow instructs the agent to run find with the user's words; the MCP configuration identifies find as a tool on DataXAPI's external server. Although the skill explains that public Douyin data is retrieved through DataXAPI, it does not warn that the user's request text is also sent there and could contain private context.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx dataxapi'.

Medium
Category
MCP Rug Pull
Confidence
90% confidence
Finding

The suggested npx dataxapi and global installation commands do not specify a reviewed package version, allowing executable dependencies to change between runs. A compromised future release could execute with the agent's local permissions and potentially access the API key or local files; this is a CLI supply-chain issue, not an unpinned MCP server version as the finding suggests.

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 60)May include surrounding context.

dataxapi call douyin.trends.list --max-price 0.002

text

**MCP.** Server `https://api.dataxapi.com/mcp`, header `Authorization: Bearer <key>`. Tools: `find` (with `platform: "douyin"` it lists this platform's endpoints), `describe` (parameters and price), `call`, `read_more` (free), `account` (balance). Setting the server up: https://dataxapi.com/agents.md

```json
{"capability":"douyin.trends.list","max_price":"0.002"}

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 69)May include surrounding context.

REST:

bash
curl -G "https://api.dataxapi.com/v1/douyin/trends/list" \
  -H "Authorization: Bearer $DATAXAPI_API_KEY"

Scope Creep

Low
Category
Excessive Agency
Confidence
70% confidence
Finding

Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.

Content

Scanner excerpt · SKILL.md (reported line 92)May include surrounding context.

md
. As recorded, the tool picks from what was published on the last day or two of the span, not from all of it: set the end date to the day you want. One page; no view counts. | $0.002 per call | up to 20 |
| `douyin.index.creators.audience.get` | Douyin trend-index creator follower profile (抖音巨量算数达人粉丝画像) | Get who follows a Douyin account from the platform's own index tool, by the account's numeric ID: the share of each segment by gender, age, province, city, city tier, phone brand and interest. Not limited to marketplace creators; shares only, no head counts. | $0.002 per call | one object |
| `douyin.index.creators.metrics` | Douyin trend-index creator core metrics (抖音巨量算数达人核心指标) | Get a Douyin creator's core figures from the platform's own index tool, by the account's numeric ID: new likes, shares and comments a day and the tool's own count of follows a day, on average over the last week and the last month, each as a ratio against the period before. The follows are not the net gain i