Security audit

Aeon Proactivity

Security checks for vulnerabilities and agentic risk

Overview

This skill is not malicious, but it should be reviewed because it persistently records broad conversation and behavior history without clear opt-in, retention, or redaction controls.

Install only if you want an agent to keep local cross-session notes about your work habits, preferences, reminders, and configuration changes. Review or delete its memory files regularly, avoid using it around secrets or personal data, and require confirmation before it stores or reuses long-term learnings.

A.I.G

Vulnerability Patterns

Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
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

Warning

Location: SKILL.md:61
Finding: Persistent User-Controlled Learnings Can Poison Future Agent Behavior
Content: View full analysis
Remediation: View remediation

T09 · Insecure Skill Coding Practices

Warning

Location: SKILL.md:101
Finding: Automatic Context Logging Can Persist Sensitive User and Configuration Data
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Rogue AgentSelf-Modification, Session Persistence
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands

Findings (5)

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The manifest description is written only in Chinese ('AEON主动伙伴技能包...') while the rest of the document is in English, and there is no indication that this language choice is optional or region-specific. That creates a locale/language policy concern because the skill presents a fixed language without user opt-in.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The skill explicitly remains active during ordinary conversation and continues monitoring for feedback, clarification opportunities, preferences, emotions, and patterns without a narrow activation boundary. That broad always-on scope increases the chance of collecting and persisting more user data than necessary, and it makes autonomous prompting/logging behavior occur in contexts where the user did not clearly request memory or analysis features.
Content: No source excerpt is available for this finding.

Session Persistence

Medium

Category: Rogue Agent
Confidence: 91% confidence
Finding: The skill is designed for cross-session persistence of reminders, preferences, corrections, and behavior patterns, and it proactively offers to create shortcuts or automations based on observed repetition. Persistent behavioral profiling can expose sensitive habits over time and may cause the agent to act on stale or overly broad inferences across sessions without renewed consent.
Content: Scanner excerpt · SKILL.md (reported line 108)May include surrounding context.
When Pattern Detected:

text
"I notice you often [pattern]. Would you like me to create a shortcut?"

Autonomous Decision Making

Medium

Category: Excessive Agency
Confidence: 85% confidence
Finding: Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
Content: Scanner excerpt · SKILL.md (reported line 361)May include surrounding context.
md
❌ Don't repeat mistakes ❌ Don't ignore feedback ❌ Don't push suggestions aggressively ❌ Don't skip confirmation on risky actions ❌ Don't pretend to be correct ---

Excessive Permissions

Low

Category: Privilege Escalation
Confidence: 80% confidence
Finding: Skill requests more permissions than appear necessary for its stated functionality. Review if elevated access is justified.
Content: Scanner excerpt · SKILL.md (reported line 17)May include surrounding context.
md
## Permissions **Declared permissions:** - `localStorage.read` — read saved notes and learnings - `localStorage.write` — save notes to local files

Static analysis

No suspicious patterns detected.