Back to skill

Security audit

Backup Validator

Security checks for vulnerabilities and agentic risk

Overview

This skill is a local backup validation guide that scans OpenClaw backup files for structure, compatibility, and leaked secrets, with no hidden execution or exfiltration behavior found.

Install only if you want an agent to inspect OpenClaw backup/workspace files for structure and possible secrets. Review any reported secret matches manually, avoid sharing full scan output publicly, keep EXTRA_PATHS limited, and do not allow git reset --hard or permission-changing recovery steps unless you explicitly intend them and have a backup.

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
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (7)

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 164)May include surrounding context.

md
Untuk setiap `SKILL.md` di `workspace/skills/`:

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 172)May include surrounding context.

md
Untuk setiap `SKILL.md` di `workspace/skills/`:

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 301)May include surrounding context.

md
Untuk setiap `SKILL.md` di `workspace/skills/`:

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
96% confidence
Finding

The skill recommends git reset --hard as a remediation path for modified files, which is a destructive command that irreversibly discards uncommitted changes. In an agent-executed or semi-automated context, this creates a serious risk of unintended data loss and could be abused to erase user work under the guise of cleanup.

Content

Scanner excerpt · SKILL.md (reported line 213)May include surrounding context.

md
- `git status --porcelain` harus kosong setelah commit
- Jika ada modified tetapi belum di-commit:
  - laporkan WARNING
  - minta commit atau `git reset --hard` jika aman
- Jika ada untracked file penting:
  - laporkan WARNING
  - minta `git add` atau sesuaikan `.gitignore`

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The phrase 'Use when the conditions in the description are met' does not state concrete activation conditions in this file and requires readers to consult another document. In a markdown file, this lack of specificity can lead to unclear or overly broad invocation because no explicit triggers, boundaries, or negative examples are provided here.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill instructions and operational guidance are written in Indonesian and do not indicate that the user may choose another language. Under the policy, forcing a specific language without opt-in is a natural-language policy violation unless clearly justified as region-specific.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The 'Common Mistakes', 'Red Flags', and 'Quick Reference' sections emphasize integrity checking via hashes and restore verification as expected validation behavior. However, the defined execution steps only cover structure, secret leaks, git state, compatibility, and metadata consistency, with no actual hash verification or restore test step, creating a documentation-to-behavior contradiction within the skill file.

Content

No source excerpt is available for this finding.