Security audit

roman-urdu-wp-seo

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed offline editorial helper for Roman Urdu/Hinglish WordPress SEO and does not show hidden access, persistence, credential use, or automatic site changes.

Install only if you want an editorial SEO workflow for WordPress content aimed at readers who search in English, Roman Urdu, or Hinglish. Review generated phrasing and any time-sensitive SEO claims before publishing, and only authorize actual WordPress changes through a trusted authenticated workflow.

A.I.G

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

SkillSpector

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 (6)

Tp4

High

Category: MCP Tool Poisoning
Confidence: 97% confidence
Finding: The declared description presents a broad WordPress SEO optimization capability, including keyword variants plus meta tags, image alt-text guidance, and technical SEO checks for South Asian audiences. The actual code only implements one narrow subset: generating Roman Urdu/Hinglish keyword suggestions offline from predefined mappings and simple template-based fallbacks. It has no WordPress integration, no content analysis, no metadata generation, no image handling, and no technical SEO validation. While the keyword-variant portion aligns partially with the description, the primary purpose and implemented scope are materially narrower than declared, so this is a mismatch.
Content: No source excerpt is available for this finding.

Tp4

High

Category: MCP Tool Poisoning
Confidence: 94% confidence
Finding: The code only creates simple metadata drafts (title, meta description, slug) from user-supplied inputs and reports character-length heuristics. While this partially aligns with the 'blended meta tags' portion of the description and is targeted toward Roman Urdu/Hinglish phrasing for Pakistani readers, it does not implement several prominently declared capabilities: keyword variants, image alt-text guidance, or technical SEO checks. Its primary behavior is narrower than the declared purpose, so the description materially overstates what the code actually does.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The description states the skill is for 'Pakistani and South Asian audiences,' which imposes a locale-specific scope in the natural-language behavior of the skill. While later sections discuss checking audience, the top-level description does not explicitly present this as an opt-in or clearly justified compliance-bound restriction.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: This code describes and defaults the skill to produce 'English + Roman Urdu/Hinglish' metadata, and its help text steers users toward Pakistan/Roman Urdu phrasing. The policy category covers language or locale constraints that are forced without offering a user language choice or documenting a justified regional restriction.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 79% confidence
Finding: The file is a guide specifically directing output toward Roman Urdu and English code-mixing, which is a language/locale constraint. While the document later adds nuance about audience and geography, the title and opening framing still prescribe a specific language mode without explicitly stating that this should only be used when the user or target audience has requested it.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The module description states it generates only Roman Urdu/Hinglish keyword suggestions, and the implementation is built around Pakistan/Roman Urdu phrasing. This enforces a specific language/locale behavior rather than offering the user a choice or documenting opt-in, which matches the language/locale policy concern.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.