ClawHub
Back to skill

Security audit

flight-delay-compensation

Security checks for vulnerabilities and agentic risk

Overview

This is an offline flight-compensation helper whose main risk is that optional saved claim letters can contain personal travel details.

Before installing, understand that generated claim letters and any JSON exports are local files you explicitly ask the tool to create. Save them in a private folder and review letters before sending, especially if you add bank details or contact information.

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
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (5)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding

The skill advertises that it works offline and includes shell-based example execution plus claim-letter file output, but it does not declare any explicit tool scope such as allowed tools or permissions. When a skill can plausibly invoke shell, read files, or write files without an explicit boundary, an agent runtime may grant broader capabilities than intended, increasing the risk of unintended command execution or file access.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The JSON export persists trip and claim details to disk without notice, including route, carrier, disruption facts, eligibility, and potentially baggage/claim-related notes. While this is not active data theft, the skill context involves travel history and dispute information that can be sensitive in agent environments, especially if logs, artifacts, or shared directories are accessible to others.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The script writes a generated claim letter to an arbitrary path without warning that the file may contain sensitive personal data and banking details, including passenger name, booking reference, contact information placeholders, and an IBAN field. In shared machines, synced folders, or agent-managed workspaces, this can create unintended persistent exposure of sensitive data even though there is no direct exfiltration in the code.

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 · scripts/test_flight_claim_checker.py (reported line 16)May include surrounding context.

python
def run(*args):
    return subprocess.run([sys.executable, str(SCRIPT), *args],
                          capture_output=True, text=True)

Description-Behavior Mismatch

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

The manifest describes a skill focused on compensation for delayed, cancelled, or overbooked flights under specific passenger-rights regimes, plus claim letters for those disruptions. The code documentation and logic also cover baggage issues under the Montreal Convention, including delayed, lost, and damaged baggage, which is a distinct claim area not mentioned in the manifest description.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.