T09 · Insecure Skill Coding Practices
Error
- Location
scripts/publish.py:11- Finding
Directory Packaging Follows File Symlinks and May Upload Files Outside the Source Directory
- Content
View full analysis
- Remediation
View remediation
Security audit
tc-protohub
Security checks for vulnerabilities and agentic risk
Overview
The skill mostly does what it says, but its packaging and upload tool can unexpectedly send files outside the chosen prototype folder and can send API credentials over non-local HTTP.
Install only if you trust the prototype directories and server configuration. Avoid publishing untrusted folders or folders containing symlinks, review contents before upload, use HTTPS for any non-local ProtoHub URL, and confirm the prototype ID before updates because updates overwrite remote content.
Vulnerability Patterns
- 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
- 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 (2)
T09 · Insecure Skill Coding Practices
Warning
- Location
scripts/publish.py:34- Finding
API Credentials and Prototype Data Can Be Transmitted over Plaintext HTTP
- 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 (4)
Undeclared Tool Scope
Medium
- Category
- MCP Least Privilege
- Confidence
- 86% confidence
- Finding
The skill advertises capabilities that read environment variables, access local files, and perform network operations, but it does not declare any explicit tool scope such as permissions or allowed-tools. That creates an authorization and transparency gap: an agent may invoke sensitive capabilities without clear least-privilege constraints or user-visible boundaries.
- Content
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 92% confidence
- Finding
The usage guidance instructs the agent to publish and overwrite remote prototypes, including updating an existing prototype by ID, but does not prominently warn that these operations modify remote state. In an agent setting, insufficient disclosure around destructive or state-changing actions increases the risk of unintended overwrites, data loss, or changes to the wrong remote resource.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 88% confidence
- Finding
The manifest description is written in Chinese while the rest of the skill documentation is in English, and there is no indication that the user can choose their preferred language. This can violate language/locale policy when a skill implicitly forces or assumes a language without explicit opt-in or documented justification.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 93% confidence
- Finding
The script’s user-facing docstrings, CLI descriptions, status messages, and error output are written in Chinese throughout, including the main command description and runtime messages. This imposes a specific language on all users without offering a locale choice or documenting a justified regional restriction, which matches the natural-language locale policy concern.
- Content
Static analysis
No suspicious patterns detected.