Back to skill

Security audit

code-debug-companion

Security checks for vulnerabilities and agentic risk

Overview

This debugging skill is coherent, but it may send error details to web search and write code or tests without clearly requiring user approval.

Install only if you are comfortable with an agent-assisted debugging workflow that may use external search and produce code or test changes. Review any stack traces for secrets or proprietary details before searching, and require manual review before applying changes or creating GitHub issues.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (9)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill documentation says it will send error, stack trace, or related code context to external search services, but it provides no privacy or data-handling warning. Debug data often contains proprietary code, secrets, internal paths, tokens, or customer information, so forwarding it to third-party services can cause unintended data leakage.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The README explicitly describes automatically writing code changes and creating test files, but it does not mention any user confirmation, review gate, or dry-run mode. In an agent skill, this can lead to unintended or unsafe modifications to a repository, especially if the diagnosis is wrong or the scope of changes expands beyond what the user expected.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger list includes very broad, common terms such as '调试', 'debug', and '修复', which can cause the skill to activate in contexts the user did not intend. Because this skill chains multiple debugging and remediation actions, over-broad activation increases the chance of unintended code-analysis or downstream write-capable operations being invoked.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly states it can write fix code and create GitHub issues, but it does not clearly warn users that these are write-side effects. In an agent environment, hidden mutation capabilities can lead to unintended repository changes, noisy issue creation, or abuse if the skill is triggered accidentally or with ambiguous input.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The trigger list contains very broad terms such as "debug", "调试", "修复", and "报错", which can cause the skill to activate in situations where the user did not intend to invoke a code-modifying debugging workflow. Because this skill can generate repair code, tests, and structured remediation steps, accidental activation increases the chance of unnecessary file changes, unintended tool use, or disclosure of sensitive debugging context.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The workflow sends extracted error keywords to an external search skill targeting third-party sources like StackOverflow, GitHub Issues, and official documentation without warning that debugging details may leave the local environment. Error messages, stack traces, filenames, or embedded tokens can contain sensitive internal information, so silent transmission to external services creates confidentiality and compliance risks.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The workflow explicitly generates repair code and unit tests but provides no user-facing warning that project files may be created or modified as part of the process. In a debugging context this is risky because users may expect analysis-only assistance, while the skill proceeds toward actionable code and test artifacts that could alter a repository or be applied without adequate review.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

The README is entirely written in Chinese and brands the assistant as a Chinese-language helper, but it does not mention whether users can choose another language. Under the policy, forcing a specific language without opt-in can be a natural-language policy violation unless the locale limitation is explicitly justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
72% confidence
Finding

The skill description, workflow actions, and output templates are entirely specified in Chinese, which may impose a language preference on users without opt-in. There is no indication that users can choose another language or locale for responses.

Content

No source excerpt is available for this finding.