ClawHub
Back to skill

Security audit

uas-ops-checker

Security checks for vulnerabilities and agentic risk

Overview

This is a local drone-compliance classification helper with disclosed decision-support limits and no evidence of hidden network, persistence, credential, or destructive behavior.

Install only if you want a decision-support helper for China-focused drone classification. Treat its legal/regulatory output as non-authoritative, verify clauses and thresholds against current official sources, and consider narrowing tool permissions because Write and WebFetch are listed but not needed for the documented CLI workflow.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (10)

Anti-Refusal Statement

High
Category
Anti-Refusal
Confidence
80% confidence
Finding

Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.

Content

Scanner excerpt · SKILL.md (reported line 116)May include surrounding context.

md
### V. Exit codes
| rc | Meaning | Trigger |
|---|---|---|
| 0 | done, no warnings | complete params, micro/light grade |
| 1 | done with warnings | incomplete input (strict presumption) or small/medium/large |
| 2 | input insufficient/invalid | no args, non-numeric, empty > mtow, non-positive |

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

This markdown file contains user-facing operational instructions exclusively in Chinese, including the title, purpose, and agent behavior guidance. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless a justified locale constraint is documented, which is not present here.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
86% confidence
Finding

The skill documentation is predominantly in Chinese and presents key operational guidance, warnings, and outputs in that locale without stating that users may choose another language. This can violate the language/locale policy because the skill appears to impose a specific language by default rather than offering opt-in or alternatives.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The description lists activation terms including “合规” and “判定器”, which are generic words rather than narrowly scoped invocation phrases. Without clearer constraints or exclusion examples, the skill could be invoked for many unrelated compliance or classification requests.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

“当用户需要无人机运营合规分类判定器相关能力时” is circular and does not clearly distinguish in-scope from out-of-scope requests. Combined with generic trigger words, it leaves activation boundaries underspecified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The file’s natural-language description, CLI help text, warnings, and output strings are consistently hard-coded in Chinese, indicating the skill is designed to operate in a single language. The policy allows locale constraints only when user choice is offered or the restriction is clearly documented and justified; this file does not provide such an opt-in or explicit justification.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
78% confidence
Finding

The document includes a dedicated Chinese activation section and Chinese trigger guidance, which may steer use toward a specific language or locale. Although the file is bilingual overall, the trigger policy does not explicitly state that users may invoke the skill in either language.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

The file content is entirely in Chinese and does not indicate that other languages are supported or that Chinese is a required locale for this skill. Under the policy for natural-language violations, forcing a specific language without user opt-in can be a locale-policy issue.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

This JSON file includes a natural-language note entirely in Chinese, which may impose a language requirement on readers without any opt-in or explanation. The policy scope for SQP-3 applies to all file types, including config/JSON files, when they force a specific language or locale.

Content

No source excerpt is available for this finding.

Dynamic attribute access via getattr()

Low
Category
Dangerous Code Execution
Confidence
50% confidence
Finding

Dynamic getattr() with a non-literal attribute name can access arbitrary object attributes, potentially bypassing access controls.

Content

Scanner excerpt · uas-ops-checker.py (reported line 213)May include surrounding context.

python
# 进程退出码遵循本技能库约定：0＝案例全部执行完毕 / 2＝存在输入错误。
        # 各案例的实际 rc 见 IR 的 rc 字段（可为 0/1/2），--demo 不代替单次调用的 rc 语义。
        sys.exit(0 if allok else 2)
    args = {k: getattr(ns, k) for k in argnames}
    try:
        res, rc = _run(args)
    except GateError as e: