Back to skill

Security audit

offline-knowledge-alignment

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only skill for aligning offline knowledge bases with online verification workflows, with no executable payload or hidden persistence found.

Installers should treat this as a Chinese-first methodology skill that may activate on broad knowledge-related terms. Review any proposed WebSearch-backed updates or Write changes to local knowledge bases, especially for regulatory or medical reference content.

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 (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) |

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
84% confidence
Finding

The natural-language notice at the top is written primarily in Chinese and presents the operative scope statement in that language, without offering an explicit language choice or explaining a required locale-specific constraint. Under the policy for natural-language content, this can be interpreted as forcing a specific language without user opt-in.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The trigger keywords are extremely generic terms like "offline", "knowledge", and "alignment", which are likely to match ordinary user discussion rather than a deliberate invocation of this skill. That can cause unintended skill activation, injecting this skill’s instructions and governance text into unrelated conversations, which increases prompt-scope confusion and may interfere with safer or more relevant skills.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The manifest description is written entirely in Chinese and does not indicate that users may choose another language or that the skill is restricted to a Chinese-language or China-specific deployment context. This creates a natural-language locale policy concern because the skill presentation appears to enforce a specific language by default.

Content

No source excerpt is available for this finding.