Back to skill

Security audit

Wake-up On LAN (WOL) API

Security checks for vulnerabilities and agentic risk

Overview

This skill is a scoped WOL API helper that handles credentials and user-confirmed ordering or registration actions without hidden persistence or unrelated access.

Install this only if you intend to let the agent interact with your WOL account. Review previews carefully before confirming purchases, registration changes, cancellations, or seat changes, and do not paste API tokens into chat; use the provided token setup or WOL_API_TOKEN instead.

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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Rogue AgentSelf-Modification, Session Persistence
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (4)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
94% confidence
Finding

The skill declares no explicit tool restrictions even though its instructions clearly rely on shell execution, environment access, file writes, and network connectivity. Without a scoped allowlist, a hosting agent may grant broader-than-necessary capabilities, increasing the blast radius if the skill is misused, prompt-injected, or its bundled script is compromised.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
80% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 25)May include surrounding context.

The script finds the token by itself, so never handle it yourself.

  • Never echo, print, cat, log or export the token, and never put it in a command line.
  • Never ask the user to paste the token into the chat. If they paste one anyway, don't repeat it. Tell them to revoke it at https://wollan.nl/user/api-tokens and create a new one.
  • To check the setup, run auth. It shows where the token comes from (hidden) and verifies it against the API.
  • If no token is configured (exit code 2), ask the user to create a token at https://wollan.nl/user/api-tokens and run the command below themselves in a terminal. It prompts for the token with hidden input and stores it in ~/.config/wol/token (mode 600). They can also set WOL_API_TOKEN in their environment instead.
    bash

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 25)May include surrounding context.

The script finds the token by itself, so never handle it yourself.

  • Never echo, print, cat, log or export the token, and never put it in a command line.
  • Never ask the user to paste the token into the chat. If they paste one anyway, don't repeat it. Tell them to revoke it at https://wollan.nl/user/api-tokens and create a new one.
  • To check the setup, run auth. It shows where the token comes from (hidden) and verifies it against the API.
  • If no token is configured (exit code 2), ask the user to create a token at https://wollan.nl/user/api-tokens and run the command below themselves in a terminal. It prompts for the token with hidden input and stores it in ~/.config/wol/token (mode 600). They can also set WOL_API_TOKEN in their environment instead.
    bash

Sudo/Root Execution

Medium
Category
Privilege Escalation
Confidence
80% confidence
Finding

Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.

Content

Scanner excerpt · scripts/wol.py (reported line 104)May include surrounding context.

python
if os.path.isfile(path):
        mode = os.stat(path).st_mode
        if mode & (stat.S_IRWXG | stat.S_IRWXO):
            print(f"warning: {path} is readable by other users; run: chmod 600 {path}", file=sys.stderr)
        with open(path, encoding="utf-8") as fh:
            tok = fh.read().strip()
        if tok:

Static analysis

No suspicious patterns detected.