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
Security audit
git-commit-helper
Security checks for vulnerabilities and agentic risk
Overview
This skill is a straightforward commit-message helper that reads git diffs and suggests Conventional Commit messages, with no evidence of hidden persistence, network access, or unrelated data handling.
Install only if you are comfortable with the agent reading staged or unstaged git diffs to draft commit messages. Review the generated message before using it, especially in repositories where diffs may contain secrets or sensitive business details.
Vulnerability Patterns
- 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
- Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
- MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 90% confidence
- Finding
The trigger language includes broad phrases like "help me commit" and "what should my commit message be," which can cause the skill to activate in general contexts beyond its narrow purpose. Overbroad activation increases the chance that repository diffs or sensitive staged content are pulled into the workflow unnecessarily, exposing code or secrets to a component when the user may not have intended that level of analysis.
- Content
Missing User Warnings
Low
- Category
- Not specified by scanner
- Confidence
- 84% confidence
- Finding
The instruction to "present to user or pass to
git commit -m" encourages direct operational use of generated output without an explicit user review or confirmation step. In context this is not highly dangerous, since the output is only a commit message, but it can still lead to accidental use of inaccurate, misleading, or sensitive text derived from the diff.- Content
Static analysis
No suspicious patterns detected.