Back to skill

Security audit

passport-expiry-radar

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marks this passport-expiry tracking skill suspicious because its findings raise concerns about sensitive registry data, when that data may be checked, and its undeclared file access; the scanners reported no specific malicious behavior.

Before installing, consider whether you want a skill that stores family document details across sessions and may check them when travel is mentioned. Review what information it stores and whether you can control access, retention, and when checks occur; the verdict is suspicious, so install only if these tradeoffs are acceptable.

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
  • 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 (4)

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

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.

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 · SKILL.md (reported line 26)May include surrounding context.

md
- Periodic audit ("what expires in the next 12 months across the family?").

## Steps
1. Load or create the registry (`~/.passport_radar.json` or a path the user gives). Each entry: traveler, doc type, issuing country, number suffix (never store full numbers unless the user insists), issue date, expiry date, blank pages (optional).
2. `status` → list every doc with days-to-expiry and a band:
   - **EXPIRED** (< 0 days) — renew immediately, travel blocked.
   - **RENEW NOW** (< 90 days) — routine processing windows no longer comfortable.

The workflow creates a persistent family identity-document registry without a privacy warning.

Medium
Category
Output Handling
Confidence
87% confidence
Finding

The workflow directs persistent storage of family identity-document metadata, potentially including children's records and full document numbers, without specifying informed consent, access restrictions, or retention controls. A local JSON registry is not inherently unsafe, and suffix-only storage reduces exposure, but unintended access or backup synchronization could disclose a useful collection of personal information; the script's actual protections are not available for verification.

Content

No source excerpt is available for this finding.

An upcoming international trip alone triggers a document-registry check, even without a document-validity request.

Low
Category
Trigger Abuse
Confidence
94% confidence
Finding

A casual mention of international travel automatically triggers access to a sensitive family document registry, without an explicit validity request or consent gate. Combined with the instruction to print a family dashboard, this can unnecessarily expose relatives' document information in an unrelated or shared conversation, although proactive travel checking is a legitimate feature.

Content

No source excerpt is available for this finding.