Security audit

documentation-engineer

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-focused skill with expected guidance around building and improving docs, but users should apply normal privacy controls before enabling analytics.

Before installing, treat this as a documentation automation helper that may lead the agent to inspect docs, APIs, workflows, feedback, and analytics. If it is used to add tracking or collect search/feedback data, require consent, minimize captured data, avoid sensitive query logging, and keep analytics configurable or disabled where appropriate.

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
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (2)

Vague Triggers

Medium

Confidence: 93% confidence
Finding: This markdown skill describes behavior 'When invoked' but never defines what phrases, commands, or contexts should trigger invocation. Without explicit trigger constraints or negative examples, the activation boundary is unclear and may cause unintended matching by a router or orchestrator.

Missing User Warnings

Medium

Confidence: 95% confidence
Finding: The skill explicitly promotes enabling analytics tracking and later references collecting usage analytics, search query analysis, and feedback data, but provides no privacy notice, consent requirement, data minimization guidance, or restriction on sensitive data capture. In a documentation context, this can lead to silent collection of user behavior or search terms that may contain personal, proprietary, or security-relevant information.

Static analysis

No suspicious patterns detected.