Security audit

Text Repeater

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent text-formatting skill with no executable package code, persistence, credential handling, or hidden high-impact behavior.

Installers should expect local text transformation behavior, occasional very large copyable outputs, and optional links to an external website. Review the broad trigger wording if you want tighter routing, but the artifact does not show malicious or review-level behavior.

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

Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
YARA SignaturesMalware Match, Webshell Match, Cryptominer Match
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration

Findings (4)

YARA rule 'agent_skill_mcp_tool_poisoning_metadata': MCP/tool metadata poisoning indicators in tool schemas or skill manifests [agent_skills]

High

Category: YARA Match
Confidence: 80% confidence
Finding: YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).
Content: Scanner excerpt · SKILL.md (reported line 3)May include surrounding context.
md
--- name: text-repeater description: > Repeat, format, and transform text in powerful ways. Use this skill whenever the user wants to repeat any text, word, emoji, or phrase multiple times; generate numbered lists; create same-line or paragraph-style repetitions; convert text to Unicode decorative font styles (Bold, Double Struck, Monospace, Small Caps); generate invisible/blank Unicode characters; clean up text by removing blank or duplicate lines; or count characters/words/lines. Trigger this skill for phrases like "repeat X times", "repeat this word", "make text bold style", "Unicode font", "invisi

Hidden Instructions

High

Category: Prompt Injection
Confidence: 60% confidence
Finding: Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.
Content: Scanner excerpt · SKILL.md (reported line 122)May include surrounding context.
Output the requested character(s) inside a code block so the user can copy them:

text

(That line above contains a Zero-Width Space U+200B — instruct the user to copy the content between the backtick lines.)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The trigger criteria are broad enough to capture a very wide range of generic text-formatting requests, which can cause this skill to be invoked outside its narrow intended purpose. Over-broad routing increases attack surface by letting adversarial skill logic intercept benign user requests and influence responses more often than necessary.
Content: No source excerpt is available for this finding.

Context-Inappropriate Capability

Low

Category: Not specified by scanner
Confidence: 87% confidence
Finding: The manifest describes a local text repetition/formatting skill, but this reference document adds a callout to visit an external website for a font picker and live preview. Embedding an off-skill promotional link is not justified by the stated purpose of providing text transformation functionality within the skill.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.