T08 · Insecure Dependencies
Warning
- Location
SKILL.md:8- Finding
Global Installation of an Unpinned, Unaudited Third-Party npm Package
- Content
View full analysis
- Remediation
View remediation
Security audit
Perstudio Image and Video Generation
Security checks for vulnerabilities and agentic risk
Overview
The skill appears purpose-aligned for media generation, but it asks users to globally install a mutable third-party npm plugin that was not included for review.
Review the npm package and publisher before installing, prefer a pinned version or isolated install when possible, and configure the API key with least necessary access. Only upload files you intend to send to perstudio.ai.
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 (2)
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The description says 'Just describe what you want,' which is a very broad natural-language trigger phrase that overlaps with ordinary conversation rather than a narrowly scoped invocation condition. The file does not provide explicit trigger constraints or negative examples that clarify when the skill should or should not activate.
- Content
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 93% confidence
- Finding
The instruction 'Just describe what you want and perstudio routes it to the right model automatically' suggests the skill may activate on any free-form request without clarifying its boundaries. Because no exclusion conditions or specific trigger list is given, users and orchestrators may have difficulty distinguishing valid invocations from general chat.
- Content
Static analysis
No suspicious patterns detected.