Back to skill

Security audit

identity-verify

Security checks for vulnerabilities and agentic risk

Overview

This is a mostly documentation-only identity-labeling skill with some broad triggers and overbroad declared tools, but no code, persistence, exfiltration, or hidden execution was found.

Install only if you want a Chinese-oriented identity/session-entry labeling helper. Review the broad trigger phrases and declared tool list first, because accidental activation and unnecessary Write/WebSearch authority are the main practical concerns.

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
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 80)May include surrounding context.

md
| 文档与理论文本 | 本 `SKILL.md`、`README.md`、其中「理论依据」段与一切理论表述 | **不在 MIT 覆盖范围内**:保留所有权利(All rights reserved) |

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The trigger keywords identity and verify are broad, generic terms that can appear in ordinary conversation, making accidental invocation of this skill more likely. In this skill’s context, unintended activation could cause the agent to answer identity/entry-point questions when the user did not intend to invoke a special skill, creating confusion about session identity or authority rather than direct code execution or data exfiltration.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The description embeds a long trigger list containing broad, everyday phrases such as '你是谁' and '新会话开场自检', which increases the chance of unintended activation during normal conversation. In an identity-labeling skill, accidental invocation can misclassify the session entry point or inject misleading identity framing into unrelated conversations, creating confusion and trust issues even if it does not directly execute code.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
81% confidence
Finding

The skill description is written to operate in Chinese and references fixed Chinese response behavior without any user opt-in or locale-scoping, which can cause the skill to override expected language behavior for users in other locales. In a skill that answers identity and session-origin questions, forced language behavior can amplify confusion, lead to incorrect user interpretation, and reduce transparency about what the system is asserting.

Content

No source excerpt is available for this finding.