Back to skill

Security audit

回译反思法

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed Chinese-Vietnamese translation QA workflow skill with no executable code, hidden data access, or destructive behavior.

Install this only if you want a Chinese-Vietnamese translation QA workflow. Be aware that broad trigger phrases may activate it during general translation discussions, and web terminology checks may expose submitted terms or text to search providers if used.

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
  • 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 (4)

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · README.md (reported line 33)May include surrounding context.

bash
# WorkBuddy
cp SKILL.md ~/.workbuddy/skills/back-translate-reflect/SKILL.md

# CodeBuddy
cp SKILL.md ~/.codebuddy/skills/back-translate-reflect/SKILL.md

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · README.md (reported line 36)May include surrounding context.

bash
# WorkBuddy
cp SKILL.md ~/.workbuddy/skills/back-translate-reflect/SKILL.md

# CodeBuddy
cp SKILL.md ~/.codebuddy/skills/back-translate-reflect/SKILL.md

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The invocation guidance is very broad: ordinary phrases like “回译 / 反思 / 中越翻译 QA / 双模型反思流水线” could trigger the skill during unrelated conversations about translation or QA. This increases unintended activation risk, which can inject workflow instructions into normal chats and cause privacy, confusion, or prompt-context interference even if the skill itself is not overtly malicious.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
85% confidence
Finding

The description states the skill is specifically for Chinese-Vietnamese translation workflow and positions it as focusing on Vietnamese translation QA. Under the policy rule, forcing a specific language/locale without user opt-in can be a violation unless the restriction is explicitly documented as a justified region-specific constraint; here it is framed as the only operating mode rather than an opt-in choice or explicit compliance-bound limitation.

Content

No source excerpt is available for this finding.