Back to skill

Security audit

Eric's Second Brain

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese-language knowledge and routing skill with broad activation guidance, but it contains no executable code, credential handling, network behavior, or persistence mechanism.

Install this skill only if you want Eric's Chinese-language second-brain framework to broadly shape routing and answer style for engineering, life, AI, and innovation questions. Review its opinionated life and interpersonal guidance before relying on it, and require explicit confirmation before any host agent turns its memory suggestions into actual persistent writes.

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 (16)

Vague Triggers

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill metadata describes itself as the first entry point for essentially any question involving engineering, life, cognition, innovation, or AI, which is broad enough to capture many ordinary user requests. This can cause inappropriate activation, overshadow more specialized skills, and increase the chance that unrelated or sensitive requests are handled under this skill’s strong behavioral framing.

Content

No source excerpt is available for this finding.

Vague Triggers

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

The routing rule explicitly states '任何问题 → Eric's Second Brain(第一入口·全貌扫描)', creating a catch-all activation path for all questions. This is dangerous because it effectively hijacks routing precedence, making the skill an interceptor for unrelated prompts and enabling instruction overreach across domains.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The trigger examples are very broad, covering common technical, career, team, and life questions without any explicit activation limits or exclusions. In a meta-skill that acts as a first-entry router, this can cause over-activation, scope creep, and unintended interception of user requests that should be handled by narrower or safer domain-specific skills.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
78% confidence
Finding

The manifest description is written entirely in Chinese and presents the skill identity and behavior in that language without indicating that users may choose another language. This can be a language/locale policy issue when the skill effectively assumes a fixed language rather than offering opt-in or selection.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The manifest declares very broad triggers such as engineering problems, life choices, career development, AI Agent, and innovation, which overlap with common user requests and can cause this skill to activate far outside a narrowly intended scope. Because this skill is positioned as a first-entry meta-router that can invoke multiple dependent skills, overbroad activation increases the chance of unintended interception, misrouting, and unauthorized influence over unrelated conversations.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
76% confidence
Finding

The entire skill document is written as Chinese-only operational guidance and does not indicate that language choice is user-selectable or context-dependent. Under the language/locale policy, a fixed language expectation should be explicitly optional or justified rather than implicitly enforced.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The routing table uses very broad, natural-language trigger examples such as requests about job changes, team efficiency, PPT creation, or product development. In a meta-router skill that acts as a 'first entry point,' these examples can overmatch common user requests and steer conversations into this skill or its subskills without clear user intent, causing unintended prompt injection of domain-specific framing and reducing user control over tool/skill selection.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The engineering sub-skill table uses very broad trigger phrases such as generic domain terms and problem categories without clear scope boundaries, disambiguation rules, or user-consent gating. In a meta-skill that routes across many capabilities, this can cause over-triggering, unintended context capture, and misrouting of user requests into unrelated or overly powerful sub-skills.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The dependency map presents the skill as a universal 'total entry point' and meta-router without defined invocation constraints, trust boundaries, or limits on cross-skill delegation. In this context, broad top-level activation increases the chance that benign prompts are routed into sensitive domains, amplifies any downstream prompt-injection or unsafe behavior in child skills, and makes control-flow harder to audit.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The routing table uses broad, common engineering keywords such as '电路', '控制器', '创新', and '增长', which can overlap with many ordinary technical discussions. In a first-entry meta-skill that claims to trigger on almost any engineering, life, cognition, innovation, or AI question, this increases the chance of accidental invocation, scope bleed, and inappropriate delegation of user requests.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The file is entirely written as a Chinese-language persona/template for responses, including the output template at L61-L74, with no indication that users may choose another language. This can violate language/locale policy when a skill implicitly forces one language without user opt-in or a documented regional justification.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

This markdown file contains natural-language instructions and templates exclusively in Chinese, and nowhere indicates that users may choose another language or that the skill is intentionally limited to a Chinese-speaking context. Under the language/locale policy rule, forcing a specific language without user opt-in is a policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

This markdown file contains user-facing natural-language guidance exclusively in Chinese, and there is no indication that users may choose another language or that the skill is intentionally limited to a Chinese-speaking audience. That creates a language/locale policy concern under the rule for forced language without user opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
78% confidence
Finding

The natural-language instructions and usage description are written in Chinese, which can effectively force a specific language experience for users who do not read Chinese. The file does not state that the skill is region-specific or offer an alternative language or opt-in choice.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
76% confidence
Finding

The manifest’s natural-language description and author presentation are written in Chinese, but there is no indication that the skill is region-specific or that users can opt into this locale. For a general-purpose skill manifest, this can create an implicit language constraint without documented choice or justification.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

The document provides only a keyword list and common domain combinations, but does not define clear activation and non-activation boundaries. This ambiguity can cause inconsistent routing decisions and make the meta-skill trigger when the user did not intend to invoke this capability, especially given the skill's broad 'first entrance' role.

Content

No source excerpt is available for this finding.