Back to skill

Security audit

doc-legacy-extract

Security checks for vulnerabilities and agentic risk

Overview

The package claims to help extract old Word .doc files, but the inspected skill contains governance, branding, and licensing text rather than usable extraction instructions or code.

Review before installing. This does not appear to be malware, but it also does not provide the promised .doc extraction method; install only if you are comfortable with a documentation-only package and broad trigger wording, and prefer a version that adds real extraction steps or code with narrower activation scope.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (7)

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 89)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) |

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The manifest advertises a reliable .doc extraction skill, but the file contains only governance, branding, and licensing text with no operational instructions or implementation. This is dangerous because agents or users may invoke the skill expecting document-processing behavior and instead receive misleading metadata-only content, creating integrity and supply-chain trust issues in automated skill selection.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The manifest lists generic trigger keywords like "doc", "legacy", and "extract" without clarifying the activation context, scope limits, or negative examples. These terms are common enough to overlap with ordinary document-related requests and could cause unintended invocation of this skill.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The license section explicitly states there are no independent code files and that the package is purely documentation, which contradicts its presentation as a functional extraction skill. This inconsistency can be exploited to deceive downstream systems, reviewers, or users about available capabilities, undermining trust and potentially causing unsafe automation decisions based on nonexistent functionality.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The manifest description includes multiple broad trigger phrases such as '提取 doc 全文', '法规 doc 附件', and generic parser/tool names, which can cause the skill to activate outside the narrowly intended use case. Over-broad activation increases the chance that unrelated document-processing requests are routed to this skill, creating misfires, incorrect handling of inputs, or unsafe processing paths if later automation assumes the skill is appropriate.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

The file begins with licensing and scope statements only in Chinese, with limited English parenthetical fragments, which imposes a language constraint on critical usage terms. Under the policy, language restrictions should either offer a language choice or clearly justify the locale-specific requirement, neither of which is present here.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
78% confidence
Finding

The skill description is entirely in Chinese and frames usage around Chinese regulatory sources, but it does not indicate whether this language constraint is intentional, optional, or user-selectable. This can be a natural-language policy concern if the skill is expected to serve users across locales without forcing a specific language context.

Content

No source excerpt is available for this finding.