T08 · Insecure Dependencies
Warning
- Location
SKILL.md:10- Finding
Unpinned Third-Party Package Installation
- Content
View full analysis
- Remediation
View remediation
Security audit
361SCAN security check your skill python scripts
Security checks for vulnerabilities and agentic risk
Overview
This skill appears meant to scan installed skills, but it relies on an unpinned external pip package and shows unexplained safety scores that are not backed by the artifact.
Review this carefully before installing. Use an isolated environment, avoid pointing it at unrelated private directories, and prefer a version-pinned package or bundled/auditable source before trusting any SAFE score or security findings it reports.
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
- MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)
Intent-Code Divergence
Medium
- Category
- Not specified by scanner
- Confidence
- 94% confidence
- Finding
The skill claims it only scans installed skills and extracts metadata, but the example output presents a security verdict ('SAFE', score, issue counts) that implies authoritative security analysis. This mismatch can mislead users or downstream agents into trusting unverified safety assessments, creating a social-engineering and false-assurance risk even if no code execution is shown in this file.
- Content
Vague Triggers
Low
- Category
- Not specified by scanner
- Confidence
- 87% confidence
- Finding
The manifest description says the skill triggers on phrases like "list skills," which is relatively broad and could match common conversational requests about abilities rather than an explicit request to scan installed skill directories. The trigger list also uses "phrases like," implying non-exhaustive matching without clear exclusion conditions or negative examples.
- Content