Security audit

Cheeeeeeeeeer

Security checks for vulnerabilities and agentic risk

Overview

This skill provides automatic or manual encouragement messages and does not show hidden data access, persistence, privilege use, or malicious behavior.

Install this if you want an agent to offer encouragement when frustration is detected. Be aware it may respond to mild or ambiguous wording, so users who prefer no unsolicited emotional support may want stricter trigger settings or manual-only use.

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 automatic triggers are broad enough to fire on common, low-risk expressions like 'tired', 'difficult', 'confused', or repeated punctuation, which can cause unsolicited emotional analysis and intervention during normal conversation. In a support skill, this creates false positives, degrades user experience, and may surface inappropriate affective responses in contexts where the user did not ask for emotional support.

Static analysis

No suspicious patterns detected.