Back to skill

Security audit

黄金三角稳态(阿姆纳集意识锚)

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marked this skill benign because the reported findings concern broad activation, fixed bilingual output, and incomplete inspection of images, rather than clear harmful behavior; confidence is medium because only half of the components were scanned completely.

The verdict is benign, but not risk-free: Skillspector completed only 50% of component analysis, with four image files not fully interpretable and related checks degraded. Before installing, consider whether the broad activation and required Chinese-then-English output suit you, and whether you are comfortable with the incomplete image review.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (7)

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 54)May include surrounding context.

md
- `eye.png`:观测"净方向"的意象

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 55)May include surrounding context.

md
- `bagua.png`:八卦图(对称/对摆的对照参照)

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 56)May include surrounding context.

md
- `golden-steady-state.png`:黄金稳态示意(可用作图标)

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 57)May include surrounding context.

md
- `anchor-diagram.png`:意识锚结构图

The skill's applicability spans routine writing, decision-making, research, and AI output without specifying when it should activate.

Medium
Category
Trigger Abuse
Confidence
88% confidence
Finding

The skill describes itself as a universal methodology applicable to any system producing directional, auditable content, including writing, research, and decisions. Although adoption is described as voluntary, no concrete invocation condition or exclusions distinguish an explicit request for this methodology from ordinary tasks in those domains.

Content

No source excerpt is available for this finding.

Ae4

Medium
Category
analysis-evasion
Confidence
80% confidence
Finding

Suspicious Unicode normalization or mixed-script content

Content

No source excerpt is available for this finding.

L010 mandates Chinese-first text followed by a full English version without offering a user language choice.

Medium
Category
Output Handling
Confidence
91% confidence
Finding

The stated bilingual standard explicitly requires Chinese and English in a fixed order. It provides neither user opt-in nor a locale-specific justification for imposing these languages.

Content

No source excerpt is available for this finding.