Back to skill

Security audit

API集成开发助手

Security checks for vulnerabilities and agentic risk

Overview

This API-integration helper is mostly documentation and templates, but it declares broad read, write, and command-execution tools despite saying it does not execute API requests.

Review this skill before installing in an environment where tool declarations grant real access. It appears non-malicious and documentation-focused, but it should ideally remove exec and limit read/write to user-selected project files unless the publisher clearly defines when local execution is allowed.

Vulnerability Patterns
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
  • 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
Findings (1)

T05 · Unauthorized Access and Privilege Escalation

Warning
Location
SKILL.md:27
Finding

Excessive Tool Permissions Violate Least Privilege

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (6)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The description says to use the skill whenever API integration, interface docking, webhook configuration, or system connection is needed, and lists very broad audiences and scenarios. It does not define specific trigger phrases, boundaries, or negative examples beyond one excluded case, which could cause unintended invocation in many ordinary development contexts.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The description states '支持中文交互' and the feature note repeats Chinese interaction as a core capability, but the file does not offer a language choice or describe this as optional. This can violate language or locale policy if the skill defaults users into a specific language without opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The feature summary lists '中文交互' as a core capability in a way that suggests a default interaction mode, with no accompanying opt-in or alternative language behavior. Under the policy, language constraints should be optional or clearly justified.

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 166)May include surrounding context.

md
import requests
# ...
def get_oauth_token(client_id, client_secret):
        'https://api.example.com/oauth/token',
        data={
            'grant_type': 'client_credentials',
            'client_id': client_id,

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 211)May include surrounding context.

md
import requests
# ...
def get_oauth_token(client_id, client_secret):
        'https://api.example.com/oauth/token',
        data={
            'grant_type': 'client_credentials',
            'client_id': client_id,

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill presents conflicting operational boundaries: it claims it does not execute actual API requests, yet elsewhere classifies itself as MD+EXEC and discusses command execution and execution-related failure modes. This ambiguity can cause an agent or user to over-grant permissions or invoke execution paths unexpectedly, increasing the risk of network actions or shell use beyond the stated scope.

Content

No source excerpt is available for this finding.