Back to skill

Security audit

ingest-preflight

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed preflight checker for ClawHub skill publishing and its CLI/network use fits that purpose.

Install/use this only if you are comfortable with it invoking your authenticated ClawHub CLI. Run it against the specific skill folder you intend to validate, because the dry-run publish path may submit that package data to ClawHub for validation.

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

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 30)May include surrounding context.

md
- The asset folder contains at least `SKILL.md` (frontmatter with `name` and

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 42)May include surrounding context.

md
- The asset folder contains at least `SKILL.md` (frontmatter with `name` and

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

The phrase "数字资源入库" appears in the user-facing skill description, but the document does not provide an English equivalent at that point, offer a language preference, or justify a Chinese-language requirement. This can conflict with the language/locale policy because it implicitly assumes comprehension of a specific language without user opt-in.

Content

No source excerpt is available for this finding.