Security audit

DoctorClaw Social Drafter

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward social media drafting skill with optional posting integrations that are disclosed and tied to user approval.

Use this skill for drafting and revising posts. If you connect Buffer, Hootsuite, direct platform APIs, or a content calendar, keep an explicit approval step before anything is scheduled, posted, or logged.

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 (1)

Vague Triggers

Medium

Confidence: 95% confidence
Finding: The skill explicitly encourages broad on-demand invocation ('Trigger on-demand whenever you have something to share') without defining clear activation criteria, approval boundaries, or required user confirmation before downstream actions. In isolation this is low risk, but in a skill that also mentions optional scheduling and posting integrations, ambiguous triggering can cause unintended drafting or posting workflows to run on loosely related user input.

Static analysis

No suspicious patterns detected.