Back to skill

Security audit

project/8487/release

Security checks for vulnerabilities and agentic risk

Overview

This skill reads recent Git commits and helps your agent produce a three-point weekly report, with no hidden or unrelated behavior found.

Run it in the repository you intend to summarize. Commit subjects will enter your agent's context, so consider their confidentiality. Results cover the preceding seven days and filter by your configured Git author name, which may omit commits under other identities.

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
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (4)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding

Retrieving local Git configuration and commit history supports the declared purpose, and there is no evidence of unrelated access or actions. However, the code stops at returning raw commit records, leaving the report-generation portion of the description unimplemented. It also uses a rolling seven-day window rather than explicitly selecting the previous calendar week.

Content

No source excerpt is available for this finding.

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: shell.

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

subprocess module call

Medium
Category
Dangerous Code Execution
Confidence
70% confidence
Finding

subprocess module calls execute external commands. Without careful input validation, this enables command injection.

Content

Scanner excerpt · scripts/get_git_logs.py (reported line 8)May include surrounding context.

python
try:
        # Get current user
        try:
            user_name = subprocess.check_output(['git', 'config', 'user.name']).decode('utf-8').strip()
        except subprocess.CalledProcessError:
            # Fallback if git config is not set or not in a git repo
            return "Error: Not a git repository or git user.name not set."

subprocess module call

Medium
Category
Dangerous Code Execution
Confidence
70% confidence
Finding

subprocess module calls execute external commands. Without careful input validation, this enables command injection.

Content

Scanner excerpt · scripts/get_git_logs.py (reported line 24)May include surrounding context.

python
'--no-merges'
        ]
        
        logs = subprocess.check_output(cmd).decode('utf-8')
        if not logs:
            return "No commits found in the last week."
        return logs