Back to skill

Security audit

Self Intro

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple Chinese interview self-introduction writer with no executable code, persistence, credential access, or hidden system behavior.

Before installing, know that this skill will ask for resume-like details and will likely respond in Chinese. Review outputs for accuracy because it is explicitly instructed not to invent facts, and ignore or remove the optional companion-skill suggestion if you do not want promotional follow-up text.

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
Findings (1)

T01 · Skill Instruction Hijacking

Error
Location
SKILL.md:155
Finding

Unsolicited Cross-Promotion Injected into Skill Responses

Content
View full analysis
Remediation
View remediation
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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The activation text is intentionally broad enough to trigger not only on explicit requests for a self-introduction, but also on loosely inferred interview-opening intent. This can cause the skill to activate when the user wanted adjacent help such as interview strategy, resume polishing, or general coaching, leading to misrouting and potentially inappropriate collection of detailed personal background.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill content is written to operate in Chinese and its examples, prompts, and output format implicitly force Chinese output without checking the user's language preference. This can create unsafe or poor outcomes if a user needs an English or bilingual interview introduction, because the system may produce the wrong-language content and increase the chance of user harm in a job-seeking context.

Content

No source excerpt is available for this finding.