Back to skill

Security audit

KnowAir Forecast 明气预报

Security checks for vulnerabilities and agentic risk

Overview

This weather skill is coherent and purpose-aligned, though users should understand that forecast lookups send the requested coordinates and API token to Caiyun's weather service.

Before installing, be comfortable providing a Caiyun Weather API token and sending requested forecast coordinates to Caiyun. Prefer coarse coordinates when exact location is unnecessary, and store the token only in the documented environment variable or config file.

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
  • 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 (8)

Lp1

High
Category
MCP Least Privilege
Confidence
97% confidence
Finding

The script makes outbound network requests to api.caiyunapp.com, and that capability is not covered by declared permissions. Even though network access is expected for a weather skill, undeclared external connectivity is still a security issue because it allows data transmission outside the host system without explicit user/platform approval.

Content

No source excerpt is available for this finding.

Lp1

High
Category
MCP Least Privilege
Confidence
97% confidence
Finding

The script makes outbound network requests to api.caiyunapp.com, and that capability is not covered by declared permissions. Even though network access is expected for a weather skill, undeclared external connectivity is still a security issue because it allows data transmission outside the host system without explicit user/platform approval.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill description includes very broad trigger phrases such as general weather, rain, temperature trend, and future weather requests, which can cause the skill to be invoked for many common prompts without clearly stating boundaries or selection criteria. Over-broad activation increases the chance of unnecessary tool use and unintended disclosure of user-supplied location data to the external weather API.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The documentation tells the agent to resolve coordinates and query the Caiyun Weather API, but it does not disclose that user location data will be transmitted to a third-party service. This creates a privacy risk because users may provide precise coordinates or place names without being informed that this data leaves the local environment.

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_forecast.py (reported line 11)May include surrounding context.

python
import urllib.request
import urllib.error

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

SKYCON_EN = {
    "CLEAR_DAY": "Clear", "CLEAR_NIGHT": "Clear",

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_forecast.py (reported line 185)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)

    if args.forecast_type == "hourly":

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

The example mixes English-language usage with one example that explicitly forces Chinese via --lang zh and Chinese response instructions. This can violate a language/locale policy if the skill is expected to respect the user's current language unless they explicitly opt in to a different locale.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

Line L180 limits the --lang option to en or zh, which is a natural-language locale constraint. The file does not document a region-specific justification or offer a broader user choice, so this is a language/locale policy concern under the stated rules.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.