Back to skill

Security audit

飞猪联动

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this skill suspicious because it reports a high-confidence risk that an API key and travel data could be sent to an unverified or unencrypted external service.

Consider avoiding installation until the API destination and HTTPS protections are verified, and until you understand what travel details or hotel coordinates are sent to external services. The verdict is suspicious, with medium overall confidence; the scan reports full component coverage, but its findings identify meaningful security and privacy concerns.

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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • Taint TrackingDirect Taint Flow, Variable-Mediated Taint Flow, Credential Exfiltration Chain
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (6)

Tainted flow: 'req' from os.environ.get (line 136, credential/environment) → urllib.request.urlopen (network output)

Critical
Category
Data Flow
Confidence
92% confidence
Finding

Sending the API key to the configured POI service is legitimate authentication, not inherently exfiltration. However, the code attaches the key without requiring HTTPS or constraining the destination and redirects, so an HTTP configuration or cross-origin redirect can expose the credential and location queries.

Content

Scanner excerpt · travel_agent.py (reported line 140)May include surrounding context.

python
"X-API-Key": key,
        "User-Agent": "Mozilla/5.0 (compatible; gaode-hotel/1.0)",
    })
    with urllib.request.urlopen(req, timeout=15) as r:
        return json.loads(r.read())

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: env, network, shell.

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

The search workflow lacks a privacy notice about sending the user's travel details to external services.

Medium
Category
Output Handling
Confidence
88% confidence
Finding

The workflow instructs the agent to resolve the user's destination through the Gaode POI service and retrieve hotel availability through FlyAI/Fliggy. Although the providers are identified, the skill does not warn that user-supplied destination and stay-date information is transmitted externally, potentially revealing travel plans.

Content

No source excerpt is available for this finding.

subprocess module call

Medium
Category
Dangerous Code Execution
Confidence
70% confidence
Finding

subprocess module calls execute external commands. Without careful input validation, this enables command injection.

Content

Scanner excerpt · travel_agent.py (reported line 170)May include surrounding context.

python
cmd += ["--max-price", str(max_price)]
    # up to 3 retries on timeout
    for attempt in range(3):
        res = subprocess.run(cmd, capture_output=True, text=True, timeout=60)
        if res.returncode != 0:
            if attempt < 2:
                time.sleep(2)

Tainted flow: 'cmd' from os.environ.get (line 160, credential/environment) → subprocess.run (code execution)

Medium
Category
Data Flow
Confidence
65% confidence
Finding

Data from a source is assigned to a variable that is later passed to a sink, creating a variable-mediated taint flow.

Content

Scanner excerpt · travel_agent.py (reported line 170)May include surrounding context.

python
cmd += ["--max-price", str(max_price)]
    # up to 3 retries on timeout
    for attempt in range(3):
        res = subprocess.run(cmd, capture_output=True, text=True, timeout=60)
        if res.returncode != 0:
            if attempt < 2:
                time.sleep(2)

The batch-enrichment workflow lacks a warning that it sends database-derived hotel coordinates to an external API.

Medium
Category
Output Handling
Confidence
87% confidence
Finding

The workflow instructs a script to iterate over accommodation records and call /nearby; lines L13–L14 specify sending hotel coordinates, and L55 configures an external HTTP endpoint. Although these calls are described functionally, the document does not warn users about bulk transmission of database-derived location data or the endpoint's unencrypted transport.

Content

No source excerpt is available for this finding.