T08 · Insecure Dependencies
Warning
- Location
README.md:37- Finding
Unpinned Third-Party CLI Executes Mutable Installation Content
- Content
View full analysis
- Remediation
View remediation
Security audit
Use Skills
Security checks for vulnerabilities and agentic risk
Overview
This skill coherently helps choose installed skills for complex requests, with disclosed behavior and a supply-chain hardening note for its install command.
Install this only if you want a meta-skill that may help route multi-domain requests to other installed skills. For lower risk, pin the installer and repository revision where possible, review the source before global installation, and choose Restricted mode when you want minimal extra skill involvement.
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
- 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)
Rp1
Medium
- Category
- MCP Rug Pull
- Confidence
- 70% confidence
- Finding
npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
- Content
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The example triggers include very broad natural-language requests such as rewriting a README, reviewing a change, or combining planning and implementation. That can cause the orchestration skill to activate unexpectedly for ordinary requests, changing control flow and forcing mode-selection behavior even when the user did not clearly intend to invoke this meta-skill.
- Content
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The example prompts include broad trigger phrases such as generic planning, coding, review, and documentation requests that closely resemble normal user tasks. In a skill-selection skill, this can cause unintended or overly frequent invocation, expanding the working set unnecessarily and increasing the chance that unrelated skills influence behavior or expose additional context.
- Content
Vague Triggers
Low
- Category
- Not specified by scanner
- Confidence
- 85% confidence
- Finding
The README says the skill can be selected automatically when a request is 'clearly multi-domain,' but it does not define concrete trigger criteria or exclusion examples. That ambiguity can lead to unintended invocation on normal mixed-purpose requests where users did not explicitly want this meta-skill.
- Content