Back to skill

Security audit

debug-pro

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this skill benign with medium confidence: its results suggest mostly purpose-aligned behavior, while flagging a mismatch between described and implemented capabilities and broad activation triggers.

Consider whether the described debugging features are important to you, since Skillspector reports that some are not implemented in the supplied code and the scan is partial because several referenced paths were missing. Broad triggers may also activate the skill in unrelated conversations. The benign verdict is not a guarantee of zero risk.

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 (7)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

The checklist aligns with the declared seven-step methodology, and the script is offline and dependency-free. However, its operational purpose is limited to displaying static guidance, materially narrower than the evidence-processing toolchain described. No undeclared resource access or suspicious behavior is present. This assessment applies to the supplied chunk; other, unprovided files could implement the missing capabilities.

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
91% confidence
Finding

The manifest explicitly lists these words as triggers without requiring a software-debugging request or providing exclusion conditions. They also occur in ordinary conversation and unrelated domains, potentially activating the debugging 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

Standalone trigger keywords such as “pro” and “定位” are too broad for a debugging skill.

Low
Category
Trigger Abuse
Confidence
97% confidence
Finding

The trigger list includes “pro,” “定位” (locate/position), and “修复” (repair/fix) without requiring a software-debugging context. These terms occur in unrelated requests, and the file provides no exclusion conditions or matching constraints to prevent unintended activation.

Content

No source excerpt is available for this finding.