Back to skill

Security audit

lgd-audit

Security checks for vulnerabilities and agentic risk

Overview

The scanners classified this skill as benign because its reported findings do not establish malicious behavior, though they flagged capability and command-execution concerns and the review is incomplete.

The verdict is benign with medium confidence, but benign does not mean risk-free. Consider the flagged environment capability and subprocess use before installing; the scan was partial because three local references in SKILL.md could not be resolved, so evidence about those references is incomplete.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • Taint TrackingDirect Taint Flow, Variable-Mediated Taint Flow, Credential Exfiltration Chain
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (4)

Code capability 'env' detected in scripts/lgd_audit_dispatcher.py but not covered by declared permissions.

High
Category
MCP Least Privilege
Confidence
75% confidence
Finding

The skill uses 'env' capability that is not covered by the declared 'allowed-tools' preapproval. Review the host runtime's actual enforcement policy; runtime permissions are unknown unless separately verified, and this declaration alone does not establish a permission ceiling.

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/lgd_audit_dispatcher.py (reported line 97)May include surrounding context.

python
note = "发现脚本;默认不执行(加 --execute 才实跑)"
                else:
                    try:
                        r = subprocess.run([sys.executable, script, "--help"],
                                           capture_output=True, text=True, timeout=25)
                        rc = r.returncode
                        status = "LIVE" if rc == 0 else "ERROR"

Tainted flow: 'script' from os.environ.get (line 85, credential/environment) → subprocess.run (code execution)

Medium
Category
Data Flow
Confidence
65% confidence
Finding

Data from a source is assigned to a variable that is later passed to a sink, creating a variable-mediated taint flow.

Content

Scanner excerpt · scripts/lgd_audit_dispatcher.py (reported line 97)May include surrounding context.

python
note = "发现脚本;默认不执行(加 --execute 才实跑)"
                else:
                    try:
                        r = subprocess.run([sys.executable, script, "--help"],
                                           capture_output=True, text=True, timeout=25)
                        rc = r.returncode
                        status = "LIVE" if rc == 0 else "ERROR"

Standalone triggers such as “审计” (audit) and “可追溯” (traceable) are broader than the LGD AI-governance routing purpose.

Low
Category
Trigger Abuse
Confidence
86% confidence
Finding

These generic terms can occur in requests about financial audits, supply-chain traceability, or other contexts unrelated to LGD. Although the surrounding description identifies an AI-governance use case, the trigger list does not explicitly require that context or exclude unrelated uses.

Content

No source excerpt is available for this finding.