T08 · Insecure Dependencies
Warning
- Location
SKILL.md:30- Finding
Unpinned Third-Party Python Dependencies
- Content
View full analysis
- Remediation
View remediation
Security audit
Anychunker Skills
Security checks for vulnerabilities and agentic risk
Overview
This skill is a straightforward AnyChunker usage guide, with normal dependency and data-sharing cautions for chunking and embedding workflows.
Use this skill in an isolated Python environment, pin package versions for production, and confirm before sending proprietary code, secrets, PII, or regulated documents to any external embedding or vector database provider.
Vulnerability Patterns
- Insecure DependenciesIntroduces malicious components through unsafe dependency sources
- 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
Findings (1)
Vulnerability Patterns
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)
Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md > **Language**: [English](SKILL.md) · [简体中文](SKILL_zh.md)
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The trigger description is extremely broad, covering generic requests like chunk, split, segment text, code, or long documents, as well as many related implementation details. This can cause the skill to activate in contexts where the user did not specifically ask for this library, increasing the chance of unintended tool use, misrouting, or overcollection of user content into a workflow the user did not intend.
- Content
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 90% confidence
- Finding
The recipe shows sending arbitrary text to an OpenAI-compatible embedding API over HTTP and to third-party providers without any warning that document contents may leave the local environment. In a chunking/RAG skill, users may apply this to sensitive source code, internal documents, or PII, so omission of a privacy/data-handling warning creates a real data exfiltration risk through normal use.
- Content