Security audit

Date Publisher

Security checks for vulnerabilities and agentic risk

Overview

This skill is a narrowly scoped helper for drafting and publishing a user-approved public dating profile, with explicit confirmation gates and privacy limits.

Before installing, be aware that this skill is designed to help publish a public dating profile. Use a dedicated public contact method, review each preview carefully, and only approve targets where you are comfortable with the profile, photo, account, visibility, and public URL being recorded.

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

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

Findings (1)

Credential Access

High

Category: Privilege Escalation
Confidence: 70% confidence
Finding: Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
Content: Scanner excerpt · references/platform-modes.md (reported line 27)May include surrounding context.
}

text
Never put an access token, password, recovery code, or private message in this log.

Static analysis

No suspicious patterns detected.