Security audit

Eo Ability Dream

Security checks for vulnerabilities and agentic risk

Overview

This skill is coherent and has no executable installer, but it asks for automatic analysis of real work logs and persistent pattern updates without clear scope or approval controls.

Review this skill carefully before installing with EO automation. It should be limited to explicitly selected or sanitized logs, and learned patterns should require human approval with provenance and rollback before becoming persistent. The package itself has no executable installer, so the main risk depends on how the host EO plugin implements the described automation.

A.I.G

Vulnerability Patterns

Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
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

Findings (2)

T02 · Agent Memory Poisoning

Error

Location: SKILL.md:69
Finding: Untrusted Historical Data Can Poison Persistent Agent Patterns
Content: View full analysis
Remediation: View remediation

T05 · Unauthorized Access and Privilege Escalation

Warning

Location: SKILL.md:58
Finding: Automatic Work-Log Analysis Lacks Access and Data-Minimization Boundaries
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

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

Findings (2)

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The skill explicitly claims that with the EO plugin it can automatically analyze real work logs, but it provides no notice, consent flow, data minimization rules, or retention boundaries. Real work logs commonly contain sensitive code, credentials, internal URLs, customer data, or employee activity metadata, so silent background analysis creates a meaningful privacy and data-governance risk.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 80% confidence
Finding: The visible natural-language description and usage guidance are entirely in Chinese, with no indication that other languages are supported or that the locale is intentionally constrained. This can violate language/locale policy when a skill effectively forces one language without user opt-in.
Content: No source excerpt is available for this finding.