ClawHub
Back to skill

Security audit

Surfline (public)

Security checks for vulnerabilities and agentic risk

Overview

This skill uses disclosed public Surfline endpoints and local cache/favorites files for surf reports, with no evidence of hidden credential use, exfiltration, or unsafe persistence.

Install this if you are comfortable with the skill contacting Surfline public services for searched or saved spot IDs and storing cached forecast JSON plus optional favorite spots in your home directory. Review or delete ~/.config/surfline/favorites.json and ~/.cache/surfline if you do not want that local surf-location history retained.

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
  • Rogue AgentSelf-Modification, Session Persistence
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
93% confidence
Finding

The skill advertises executable scripts that use network access and local file read/write, but the manifest does not declare any tool scope such as permissions or allowed-tools. This creates a least-privilege and review gap: an agent or reviewer cannot tell from the skill definition what capabilities are intended, increasing the chance of unintended tool use or overbroad execution in environments that honor manifest-declared constraints.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
84% confidence
Finding

The skill instructs users to create a persistent file under ~/.config/surfline/favorites.json, which introduces session persistence on the local system. Even though the stored data appears low sensitivity, persistent state can expose user preferences, be modified by other processes, or become a foothold for confusing or unsafe behavior if the skill later trusts that file without validation.

Content

Scanner excerpt · SKILL.md (reported line 30)May include surrounding context.

  1. Favorites summary (multiple spots) (prints text + JSON by default):

Create ~/.config/surfline/favorites.json (see references/favorites.json.example).

bash
python3 scripts/surfline_favorites.py

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

This code reads a local favorites file and then calls kbyg_conditions(spot_id) for each saved spot, which implies a network/API lookup based on user-configured data. The script's docstring mentions reading the local file but does not disclose that it will contact an external service for each favorite, and there is no prompt or runtime notice about that behavior.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.