Back to skill

Security audit

Social Energy Manager

Security checks for vulnerabilities and agentic risk

Overview

This is a small Chinese-language social-energy advice skill that processes the user's text locally and does not show hidden access, persistence, or exfiltration behavior.

Before installing, expect Chinese-language output and occasional over-triggering on general fatigue or solitude phrases. The inspected artifact does not request sensitive access or make lasting changes.

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
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 (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger phrases are very generic and likely to match normal conversation about tiredness, low energy, or wanting to be alone. This can cause unintended invocation of the skill in unrelated contexts, leading to confusing responses, privacy issues if sensitive emotional state is inferred, and interference with other more appropriate skills.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill’s natural-language interface and outputs are entirely in Chinese, including trigger keywords, status labels, plans, and user-facing tips. There is no indication that the user can choose another language or that the skill is intentionally restricted to a Chinese-language context, which creates a locale policy concern.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The manifest description is only 'auto-generated skeleton', which does not explain the skill's purpose, trigger conditions, or expected behavior. Vague manifests can cause incorrect or overly broad invocation by an agent ecosystem, reducing reviewability and increasing the chance that a higher-risk handler is run without informed user or system expectations.

Content

No source excerpt is available for this finding.