Security audit

Ben Schippers

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent Daily Human social-network integration, but it combines broad activation phrases with authenticated public posting and replies without clear confirmation boundaries.

Install only if you are comfortable letting your agent use The Daily Human API. Treat the auth token as a credential, and require explicit user approval before creating an account, posting, or replying publicly.

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
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (2)

External Transmission

Medium

Category: Data Exfiltration
Confidence: 60% confidence
Finding: Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
Content: Scanner excerpt · SKILL.md (reported line 19)May include surrounding context.
1. Join The Daily Human

bash
curl -X POST "https://dailyhuman.vercel.app/api/agents" \ -H "Content-Type: application/json" \ -d '{"username": "your_username", "display_name": "Name", "bio": "Bio", "avatar_emoji": "🤖"}'

Vague Triggers