Back to skill

Security audit

debug-pro

Security checks for vulnerabilities and agentic risk

Overview

The verdict is benign with medium confidence: the scanners report no findings from AIG, while Skillspector flags concerns about mismatched capability claims, broad activation terms, environment access, undeclared tool scope, and a Git command; its analysis is partial.

The verdict is benign, not risk-free. Consider whether the broad activation terms and the reported mismatch between claimed and assessed capabilities are acceptable for your use. Skillspector's analysis is partial: four local references were unresolved, and binary content was outside the analyzer's scope; AIG completed without findings.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (6)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The script matches the declared seven-step methodology and offline, zero-dependency characteristics, but its behavior is limited to printing static guidance. The description materially overstates the supplied code's central evidence-processing capabilities. No undeclared resource access, unrelated triggers, or malicious behavior is evident. This assessment is limited to the supplied code chunk; other skill materials were not provided.

Content

No source excerpt is available for this finding.

Env Variable Harvesting

High
Category
Data Exfiltration
Confidence
70% confidence
Finding

Code enumerates, copies, or searches environment variables for secrets. Bulk environment access can collect credentials unrelated to the skill's stated purpose.

Content

Scanner excerpt · tools/debughunt.py (reported line 137)May include surrounding context.

python
}
    # 白名单采集 + 强制脱敏:任何含 KEY/TOKEN/SECRET 的键不入快照
    safe_env = {}
    for k, v in os.environ.items():
        if SECRET_KEY.search(k):
            continue
        if k in ("LANG", "LC_ALL", "SHELL", "TERM", "PYTHONPATH", "VIRTUAL_ENV", "CONDA_DEFAULT_ENV"):

Env Variable Harvesting

High
Category
Data Exfiltration
Confidence
70% confidence
Finding

Code enumerates, copies, or searches environment variables for secrets. Bulk environment access can collect credentials unrelated to the skill's stated purpose.

Content

Scanner excerpt · tools/debughunt.py (reported line 143)May include surrounding context.

python
if k in ("LANG", "LC_ALL", "SHELL", "TERM", "PYTHONPATH", "VIRTUAL_ENV", "CONDA_DEFAULT_ENV"):
            safe_env[k] = v if len(v) < 120 else v[:117] + "..."
    item["env_whitelist"] = safe_env
    item["redacted_keys_count"] = len([k for k in os.environ if SECRET_KEY.search(k)])
    try:
        item["git_rev"] = subprocess.run(["git", "rev-parse", "--short", "HEAD"],
                                         capture_output=True, text=True, timeout=8).stdout.strip() or None

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

Standalone triggers such as "error", "exception", "reproduce", and "regression" are overly broad.

Medium
Category
Trigger Abuse
Confidence
93% confidence
Finding

The descriptions explicitly list common words as activation triggers without requiring a software-debugging request or providing exclusion conditions. These words also occur in ordinary conversation and other technical domains, so they could activate the skill unintentionally.

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 · tools/debughunt.py (reported line 145)May include surrounding context.

python
item["env_whitelist"] = safe_env
    item["redacted_keys_count"] = len([k for k in os.environ if SECRET_KEY.search(k)])
    try:
        item["git_rev"] = subprocess.run(["git", "rev-parse", "--short", "HEAD"],
                                         capture_output=True, text=True, timeout=8).stdout.strip() or None
    except Exception:
        item["git_rev"] = None