Security audit

Camping

Security checks for vulnerabilities and agentic risk

Overview

The skill is labeled as camping help but its instructions also cover travel booking, flight status, check-in, itineraries, and boarding passes, which is broader than users would expect.

Review this skill before installing. It does not show malware or executable behavior, but its stated camping purpose is mixed with travel-booking and airline workflow instructions. Install only if you want a broader travel assistant and are comfortable with the agent potentially handling itinerary, ticket, or boarding-pass context under a camping-labeled skill.

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

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (4)

Description-Behavior Mismatch

High

Confidence: 98% confidence
Finding: The skill is presented as a camping assistant, but its documented functions include transportation booking, flight status, boarding passes, and itinerary handling. This scope mismatch can misroute user requests, trigger the wrong skill for unrelated travel tasks, and cause the agent to expose capabilities or collect context users did not intend to share with a camping tool.

Natural-Language Policy Violations

Medium

Confidence: 91% confidence
Finding: All user-facing natural-language content in the skill is written in Chinese, and the file does not indicate that language selection is optional or user-configurable. Under the policy, a skill should not impose a specific language or locale unless the constraint is explicitly documented and justified or the user is given a choice.

Intent-Code Divergence

Medium

Confidence: 93% confidence
Finding: The heading and examples label the skill as outdoor camping, but the detailed capabilities describe airline and booking workflows. This inconsistency increases the chance of deceptive or accidental invocation, making users and orchestration systems misunderstand what the skill actually does.

Vague Triggers

Medium

Confidence: 88% confidence
Finding: The trigger examples are generic phrases like asking how to use the skill for a specific scenario or what its core functions are. Broad phrasings can overlap with normal conversation and increase unintended activation, especially when paired with the skill's already ambiguous scope.

Static analysis

No suspicious patterns detected.