ClawHub
Back to skill

Security audit

Context Verifier

Security checks for vulnerabilities and agentic risk

Overview

This skill is a local file-integrity helper that discloses its file reads and packet storage risks, with no evidence of hidden credential access or exfiltration.

Install only if you are comfortable with a skill that can hash any file path you explicitly provide. Avoid using --include-content with secrets, credentials, or broad globs, add output/context-packets/ to .gitignore, and periodically delete old packets because they are unencrypted and retained until manually removed.

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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

Credential Access

High
Category
Privilege Escalation
Confidence
60% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

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

/cv packet docs/*.md --name "docs-backup" --include-content

NEVER do this:

/cv packet .env --include-content # Stores secrets to disk!

text

### Required .gitignore Entry

Credential Access

High
Category
Privilege Escalation
Confidence
60% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 382)May include surrounding context.

/cv packet docs/*.md --name "docs-backup" --include-content

NEVER do this:

/cv packet .env --include-content # Stores secrets to disk!

text

### Required .gitignore Entry

Credential Access

High
Category
Privilege Escalation
Confidence
60% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 226)May include surrounding context.

yaml
# .openclaw/context-verifier.yaml
critical_patterns:
  - "*.env"
  - "*credentials*"
  - "*secret*"
  - "CLAUDE.md"     # Claude Code projects

Static analysis

No suspicious patterns detected.