Back to skill

Security audit

Logos(诺声)

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only persona and signing guide for Logos-branded thought-leadership content, with no code, persistence, credential use, or hidden runtime behavior.

Install this only if you want an agent to produce content in the Logos(诺声) persona and potentially include Logos attribution. For ordinary article, speech, or brand-copy requests, confirm whether you want Logos-branded signed output before publishing.

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:31
Finding

Mandatory Persona Impersonation and Attribution Injection

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)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
78% confidence
Finding

The skill is defined with a Chinese identity, naming, and output framing throughout, but does not state that users may choose another language or locale. Because the instructions consistently prescribe a single language/style context for generated public content, this can violate language/locale policy when user preference or deployment context differs.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The activation trigger is broad enough to match many ordinary writing requests such as external content creation, speeches, opinion pieces, and brand messaging. That can cause the agent to invoke this persona unexpectedly, overriding task-specific instructions or narrowing responses into branded signed output, which is a prompt-scope control issue even if not overtly malicious.

Content

No source excerpt is available for this finding.