T09 · Insecure Skill Coding Practices
Warning
- Location
scripts/budget.py:46- Finding
Unvalidated Numeric Values Can Corrupt Accounting and Bypass Budget Controls
- Content
View full analysis
- Remediation
View remediation
Security audit
Budget
Security checks for vulnerabilities and agentic risk
Overview
This skill is a disclosed local budget tracker, but users should treat its budget checks and exports as advisory rather than hardened financial controls.
Install only if you are comfortable with a local script storing transaction details on disk. Avoid putting secrets in notes, keep the data directory private, validate unusual amounts yourself, and be careful opening CSV exports in spreadsheet software.
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 (3)
T09 · Insecure Skill Coding Practices
Warning
- Location
scripts/budget.py:154- Finding
CSV Export Permits Spreadsheet Formula Injection and Row Manipulation
- Content
View full analysis
transactions.csv ...[truncated 1022 chars]- Remediation
View remediation
T09 · Insecure Skill Coding Practices
Note
- Location
scripts/budget.py:19- Finding
Financial Records Are Stored Without Explicit Restrictive Permissions
- 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 (1)
Undeclared Tool Scope
Medium
- Category
- MCP Least Privilege
- Confidence
- 86% confidence
- Finding
The skill instructs the agent to run a Python script that persists budget data to disk, but the manifest declares no explicit tool scope or permissions such as file-write access. This creates a governance gap: an agent or platform may execute file-writing behavior without clear user-visible authorization boundaries, increasing the risk of unintended filesystem modification or overbroad execution in environments that rely on manifest-declared permissions.
- Content