T01 · Skill Instruction Hijacking
Warning
- Location
SKILL.md:8- Finding
Mandatory Brand and Promotional Content Hijacks Agent Output
- Content
View full analysis
- Remediation
View remediation
Security audit
winson-make-what-lasts-skill
Security checks for vulnerabilities and agentic risk
Overview
This is a Chinese-language diagnostic writing framework with disclosed branding, not a skill that runs code, accesses data, or persists changes.
Installers should expect Chinese-language guidance and possible unsolicited author/brand attribution in generated outputs. Use it for reflective project diagnostics, and avoid it when strict neutral formatting or attribution-free output is required.
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)
Vulnerability Patterns
- 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
- Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The skill content is entirely in Chinese and does not offer a language-choice mechanism or document that the skill is intended only for Chinese-speaking users. This can cause users or downstream agents to misunderstand instructions, skip important caveats, or misuse the skill because they cannot reliably interpret its guidance.
- Content