ClawHub
Back to skill

Security audit

Ward GitHub Repo i18n

Security checks for vulnerabilities and agentic risk

Overview

This skill is a scoped repository documentation localization helper with an offline audit script and explicit guardrails around user confirmation and remote changes.

Install only if you want an agent to inspect and edit selected repository documentation for localization. Confirm the exact files, locales, and any GitHub metadata changes before use, and do not authorize remote metadata writes unless you have reviewed the final description and topic list.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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 (5)

Ae1

High
Category
analysis-evasion
Content
python3 scripts/audit_repo_i18n.py /path/to/repository \
Confidence
100% confidence
Finding
Referenced artifact was not completely inspected

Ae1

High
Category
analysis-evasion
Content
python3 scripts/audit_repo_i18n.py /path/to/repository \
Confidence
100% confidence
Finding
Referenced artifact was not completely inspected

Lp3

Medium
Category
MCP Least Privilege
Confidence
84% confidence
Finding
The skill instructs the agent to inspect repositories, read multiple files, render previews, and perform browser-based GitHub-style preview and possible remote metadata verification, but it does not declare any explicit tool restrictions or permissions. That mismatch can let the runtime grant broader file-read or network access than a user expects, increasing the risk of unintended repository inspection, data exposure, or remote interaction beyond the confirmed scope.

Scope Creep

Low
Category
Excessive Agency
Content
## Locale matrix

Build a matrix from the user's requested locales and the selected repository files. Locale identifiers are not limited to Chinese; use the user's requested language and the repository's established naming convention.

| Locale | Default path | Mirror path | Status |
| --- | --- | --- | --- |
Confidence
70% confidence
Finding
Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.

Natural-Language Policy Violations

Low
Confidence
82% confidence
Finding
The CLI defaults `--default-locale` to `en`, which establishes English as the baseline locale for parity checks unless the user explicitly overrides it. This is a natural-language locale policy concern because it privileges a specific language by default without any opt-in or justification that the tool is intended for an English-primary workflow.

Static analysis

No suspicious patterns detected.