T01 · Skill Instruction Hijacking
Error
- Location
SKILL.md:788- Finding
Mandatory Promotional Output and External Lead-Generation Hijacking
- Content
View full analysis
- Remediation
View remediation
Security audit
Competitor Benchmark
Security checks for vulnerabilities and agentic risk
Overview
The skill mainly provides competitor analysis, but it also requires promotional upsells and an external WeCom contact in generated reports.
Review this skill before installing if you want neutral reports: it can produce useful competitor analysis, but it is designed to include the publisher's paid-service recommendations and WeCom contact in outputs. Use only public, non-sensitive business information for research inputs, and verify any competitor data sourced from reviews or social platforms.
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
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- 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 (5)
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 92% confidence
- Finding
This markdown file is natural-language guidance, and all user-facing content is presented only in Chinese. Under the policy, forcing a specific language without user opt-in or a documented region-specific justification is a natural-language policy violation.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 79% confidence
- Finding
This markdown file is written entirely in Chinese and the call to action '来找我聊聊吧' implicitly directs users into a Chinese-language interaction flow. There is no indication anywhere in the file that other languages are supported or that the user may choose their preferred language, which can conflict with language/locale choice policies.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
All instructions, templates, and agent scripts in the file are exclusively in Chinese, and the skill does not mention any option for users to select another language. The policy requires flagging language or locale constraints when they are imposed without user opt-in or clear justification.
- Content
Missing User Warnings
Low
- Category
- Not specified by scanner
- Confidence
- 85% confidence
- Finding
The skill directs the agent to collect and summarize competitor information from public sources, including user reviews, social media discussions, and third-party platforms, but it does not warn users that third-party and user-generated data may be gathered and processed. This creates a transparency and privacy risk because users may not expect external personal or reputational data to be aggregated into a report, especially when the workflow explicitly includes public commentary and platform-derived information.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 92% confidence
- Finding
This markdown file presents all user-facing content in a single language and does not indicate that users may choose another language or locale. Under the policy rule for natural-language constraints, forcing one language without opt-in can be a locale-policy issue.
- Content
Static analysis
No suspicious patterns detected.