ClawHub
Back to skill

Security audit

Spacex

Security checks for vulnerabilities and agentic risk

Overview

The SpaceX lookup purpose is clear, but the README tells users to install mutable external code that is not included in the reviewed artifact.

Review the external GitHub repository and pin it to a known commit before installing. This skill appears intended for public SpaceX API lookups, but the reviewed package does not contain the executable implementation it tells agents to run.

A.I.G

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • 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
Findings (1)

T08 · Insecure Dependencies

Warning
Location
README.md:9
Finding

Unpinned Installation from a Mutable Third-Party Repository

Content
View full analysis
Remediation
View remediation

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • YARA SignaturesMalware Match, Webshell Match, Cryptominer Match
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

YARA rule 'agent_skill_mcp_tool_poisoning_metadata': MCP/tool metadata poisoning indicators in tool schemas or skill manifests [agent_skills]

High
Category
YARA Match
Confidence
80% confidence
Finding

YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).

Content

Scanner excerpt · SKILL.md (reported line 4)May include surrounding context.

name: spacex version: 1.0.0 description: "CLI for AI agents to lookup SpaceX launches and rockets for their humans. No auth required." homepage: https://github.com/r-spacex/SpaceX-API metadata: openclaw: emoji: "🚀" requires: bins: ["bash", "curl", "jq"] tags: ["spacex", "rockets", "launches", "space", "cli"]

SpaceX Lookup

CLI for AI agents to lookup SpaceX launches, rockets, and crew for their humans. "When's the next SpaceX launch?" — now your agent can answer.

Uses the community SpaceX API. No account or API key needed.

Usage

text
"What are the upcoming SpaceX launches?"
"Show me t

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · README.md (reported line 65)May include surrounding context.

md
## API Reference

- Base URL: `https://api.spacexdata.com/v4`
- [API Documentation](https://github.com/r-spacex/SpaceX-API/tree/master/docs)

## License

Static analysis

No suspicious patterns detected.