Back to skill

Security audit

eeat-content-quality-audit

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed content-audit rubric with minor usability and data-access cautions, but no evidence of hidden, destructive, or persistent behavior.

Install only if you want a structured EEAT/CORE/GEO content audit workflow. Prefer pasted content or exact URLs/paths, and avoid giving it private files unless you intend the agent to read and analyze them.

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 (14)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The trigger phrases are broad enough to match ordinary requests for writing feedback, optimization, or assessment, which can cause the skill to activate outside its intended niche. Over-broad activation can steer users into a rigid scoring workflow they did not request and may increase exposure to other risky behaviors in the skill, such as processing URLs or file paths unnecessarily.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill explicitly supports auditing user-provided URLs and file paths but does not require a user-facing consent step or safety warning before accessing external or local content. In an agentic environment, this can lead to unintended retrieval of sensitive local files or untrusted remote resources, creating privacy, data exposure, or SSRF-style access risks depending on the runtime's capabilities.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

SQP-3 applies to all file types and covers language or locale policy violations. This document is primarily in English but includes untranslated Chinese text such as '混乱', which can force a language expectation on readers without opt-in or explanation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

SQP-3 applies to all file types and covers language or locale policy violations. This document is primarily in English but includes untranslated Chinese text such as '混乱', which can force a language expectation on readers without opt-in or explanation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

SQP-3 applies to all file types and covers language or locale policy violations. This document is primarily in English but includes untranslated Chinese text such as '混乱', which can force a language expectation on readers without opt-in or explanation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

SQP-3 applies to all file types and covers language or locale policy violations. The line contains Chinese text ('不超过') embedded in otherwise English guidance, creating an implicit language requirement without user opt-in or locale justification.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

SQP-3 applies to all file types and covers language or locale policy violations. This document is primarily in English but includes untranslated Chinese text such as '混乱', which can force a language expectation on readers without opt-in or explanation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

SQP-3 applies to all file types and covers language or locale policy violations. This document is primarily in English but includes untranslated Chinese text such as '混乱', which can force a language expectation on readers without opt-in or explanation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

SQP-3 applies to all file types and covers language or locale policy violations. This document is primarily in English but includes untranslated Chinese text such as '混乱', which can force a language expectation on readers without opt-in or explanation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

SQP-3 applies to all file types and covers language or locale policy violations. The line contains mixed-language wording ('前后consistent') inside an otherwise English standard, which imposes an unexplained locale expectation on users.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

SQP-3 applies to all file types and covers language or locale policy violations. The line includes untranslated Chinese text ('次数') in an otherwise English document, with no language-selection option or locale rationale.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

SQP-3 applies to all file types and covers language or locale policy violations. The line contains mixed-language wording ('前后consistent') in an otherwise English recommendation, forcing a language assumption without user opt-in or explanation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

SQP-3 applies to all file types and covers language or locale policy violations. The line includes untranslated Chinese text ('集中在') in otherwise English content, without any documented language choice or locale constraint.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

The note says the skill primarily serves Chinese users, which establishes a locale preference in natural language. Because the file does not explicitly state that users may choose another language or output locale, this can be read as a default language policy without opt-in.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.