ClawHub
Back to skill

Security audit

KnowAir Minutely 明气分钟级降水

Security checks for vulnerabilities and agentic risk

Overview

This skill is a narrow weather lookup tool that uses a Caiyun API token and location coordinates to fetch short-term rain forecasts.

Install this only if you are comfortable providing a Caiyun Weather API token and having queried coordinates sent to Caiyun. Prefer using the CAIYUN_TOKEN environment variable and review when the skill is invoked for broad weather questions.

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
  • Rogue AgentSelf-Modification, Session Persistence
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (5)

Lp1

High
Category
MCP Least Privilege
Confidence
75% confidence
Finding

The skill uses 'env' capability that is not listed in its permissions. This may indicate deceptive intent or missing permission declarations.

Content

No source excerpt is available for this finding.

Lp1

High
Category
MCP Least Privilege
Confidence
75% confidence
Finding

The skill uses 'network' capability that is not listed in its permissions. This may indicate deceptive intent or missing permission declarations.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill description contains broad natural-language trigger phrases like 'will it rain soon' and 'should I bring an umbrella,' which can cause the skill to activate on ordinary weather-related conversation without strong user intent to invoke this specific capability. This increases the chance of unintended tool use and unnecessary external API calls, though the direct security impact is limited because the skill’s function is narrowly scoped to weather lookup.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% 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_minutely.py (reported line 11)May include surrounding context.

python
import urllib.request
import urllib.error

API_BASE = "https://api.caiyunapp.com/v2.6"


def get_token():

Session Persistence

Medium
Category
Rogue Agent
Confidence
60% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · scripts/query_minutely.py (reported line 111)May include surrounding context.

python
token = get_token()
    if not token:
        print(json.dumps({"error": "No API token found. Set CAIYUN_TOKEN env var or create ~/.config/knowair/token"}))
        sys.exit(2)

    url = f"{API_BASE}/{token}/{args.lng},{args.lat}/minutely?lang={args.lang}"

Static analysis

No suspicious patterns detected.