Security audit

SocialKit Social Core

Security checks for vulnerabilities and agentic risk

Overview

This skill provides social-media writing rules and a local approval workflow without publishing content or contacting external services.

Review each draft and media item before approving in your own terminal. Remote media can change without invalidating approval. Keep post folders trusted, and review companion publishing skills separately because their account access and posting behavior are not included here.

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
MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (4)

Incomplete referenced artifact analysis

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 54)May include surrounding context.
md
- Create: `node scripts/post.mjs --init --dir <folder> --platform <id> --kind <kind>`

Incomplete referenced artifact analysis

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 55)May include surrounding context.
md
- The user approves in their own terminal: `node scripts/post.mjs --approve --dir <folder>`

Incomplete referenced artifact analysis

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 56)May include surrounding context.
md
- Check: `node scripts/post.mjs --verify --dir <folder>` (exit 0 only if unchanged since approval)

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: env.

Medium

Category: MCP Least Privilege
Confidence: 70% confidence
Finding: Without declared permissions the skill's intent is opaque and cannot be validated.
Content: No source excerpt is available for this finding.