T08 · Insecure Dependencies
Warning
- Location
SKILL.md:297- Finding
Unpinned Third-Party Packages Create a Supply-Chain Execution Risk
- Content
View full analysis
- Remediation
View remediation
Security audit
Agentvibes Voice Skill
Security checks for vulnerabilities and agentic risk
Overview
This TTS skill appears purpose-related, but it needs review because it combines broad local execution/file authority, unpinned package installation, and unclear network/API-key disclosures.
Review before installing. Use an isolated virtual environment, avoid administrator/root installs, verify the Python packages and publishers yourself, and do not process sensitive text unless you confirm which providers run locally and which send content or credentials to third parties.
Vulnerability Patterns
- Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
- 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
Findings (2)
T05 · Unauthorized Access and Privilege Escalation
Note
- Location
SKILL.md:23- Finding
Skill Declares Unnecessarily Broad File and Command-Execution Capabilities
- Content
View full analysis
- Remediation
View remediation
Vulnerability Patterns
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (5)
Intent-Code Divergence
Medium
- Category
- Not specified by scanner
- Confidence
- 94% confidence
- Finding
The documentation makes conflicting trust and privacy claims: it says the skill is free, offline, and requires no account, while later sections instruct users to obtain HuggingFace credentials and configure API keys. This can mislead users into exposing secrets or sending data over the network under false assumptions about local-only operation.
- Content
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 91% confidence
- Finding
The skill documents translation, provider switching, and first-time voice downloads without clearly warning that user text or metadata may leave the local environment. In a TTS/translation skill, this context increases risk because users may process sensitive prompts, transcripts, or proprietary content and assume it stays local.
- Content
Intent-Code Divergence
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The FAQ minimizes network use by saying only first-time voice download needs connectivity, but setup sections describe HuggingFace registration and API-key configuration as required. Users may rely on the FAQ and unknowingly route content or credentials to third parties, creating privacy and secret-management risk through deceptive or inaccurate documentation.
- Content
Missing User Warnings
Low
- Category
- Not specified by scanner
- Confidence
- 96% confidence
- Finding
The cleanup command is described as a convenience feature but lacks a prominent warning that it deletes cached audio files. This can cause unintended loss of locally stored outputs, which is a real safety issue, though limited in severity because it affects cache data rather than arbitrary files based on the provided documentation.
- Content
Intent-Code Divergence
Low
- Category
- Not specified by scanner
- Confidence
- 81% confidence
- Finding
The documentation frames the skill as usable without an account, yet the security section warns about protecting account information. This is not merely incomplete documentation; it conveys conflicting user expectations about whether accounts are part of normal use.
- Content