T08 · Insecure Dependencies
Warning
- Location
skill.json:8- Finding
Unnecessary Registry Packages Shadow Node.js Core Modules
- Content
View full analysis
- Remediation
View remediation
Security audit
Dashboard Manager2
Security checks for vulnerabilities and agentic risk
Overview
The skill appears intended to manage a local Jarvis dashboard, but its executable behavior has broader and less clearly disclosed authority than its documentation and permissions describe.
Review this skill before installing. It may be appropriate for a trusted local Jarvis dashboard, but only if you are comfortable granting it mutation authority over the dashboard service on localhost:8009, including document deletion and automation rule changes. The publisher should update the documentation and manifests to disclose the local API access, remove unused dependencies, validate identifiers, check API failures, and add user confirmation or clear controls for destructive actions.
Vulnerability Patterns
- Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
- Insecure DependenciesIntroduces malicious components through unsafe dependency sources
- Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
- 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
Findings (4)
T09 · Insecure Skill Coding Practices
Warning
- Location
index.js:58- Finding
Unvalidated Identifiers Are Interpolated into Local API Paths
- Content
View full analysis
- Remediation
View remediation
T09 · Insecure Skill Coding Practices
Warning
- Location
index.js:31- Finding
Mutating API Functions Report Success After Failed Operations
- Content
View full analysis
- Remediation
View remediation
T05 · Unauthorized Access and Privilege Escalation
Warning
- Location
SKILL.md:116- Finding
Declared File-Only Permission Model Misrepresents Broad Local API Authority
- Content
View full analysis
- Remediation
View remediation
Vulnerability Patterns
- MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
- 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 (6)
Undeclared Tool Scope
Medium
- Category
- MCP Least Privilege
- Confidence
- 70% confidence
- Finding
Without declared permissions the skill's intent is opaque and cannot be validated.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 89% confidence
- Finding
The natural-language instructions and descriptions in this file are presented exclusively in French, including the core description, permissions, usage, and security sections. Under the policy, forcing a specific language without user opt-in or a documented regional justification is a language/locale policy violation.
- Content
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 90% confidence
- Finding
The deleteDocument function issues a DELETE request that can irreversibly remove user data, but this function has no confirmation prompt, logging, or explanatory comment warning about the destructive action. In this file, unlike createDocument, there is also no user-visible disclosure for the deletion behavior.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 92% confidence
- Finding
The natural-language description and in-code comments present the skill in French only, which can indicate a fixed language/locale assumption without user opt-in. The file does not state that the skill is region-specific or that users may choose another language.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The description is written only in French ("Gère les interactions avec le dashboard Jarvis"), which indicates a fixed language choice in user-facing skill metadata. There is no indication elsewhere in this manifest that users can choose a language or that the French-only locale is required for a justified region-specific purpose.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 91% confidence
- Finding
The manifest contains user-facing natural-language descriptions in French ("Récupère les notes", "Ajoute un log") with no indication that the skill is French-only or that users can choose their preferred language. This can violate language/locale policy when a skill imposes a language without opt-in or documented regional scope.
- Content
Static analysis
No suspicious patterns detected.