Skills
Navigate
skills/huangzida/skills/skillshare/Gen Agent Trust Hub

skillshare

Fail

Audited by Gen Agent Trust Hub on Oct 6, 2026

Risk Level: HIGHREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The script scripts/run.sh downloads a binary executable from a remote GitHub repository (runkids/skillshare) and executes it using exec. While the download process uses HTTPS, the repository is managed by an unverified third-party entity.- [COMMAND_EXECUTION]: The skill provides a CLI tool that executes system operations including symlinking (sync), moving files to a trash directory (uninstall), and Git operations (install, push, pull).- [INDIRECT_PROMPT_INJECTION]: The skill is designed to fetch and install third-party skills from arbitrary Git repositories, which exposes the agent to potentially malicious instructions.
  • Ingestion points: External Git repositories specified during installation (referenced in references/install.md).
  • Boundary markers: The tool includes an audit command and security gate as described in references/audit.md, though these are advisory and may be bypassed.
  • Capability inventory: The tool can perform file system writes, manage symlinks, and execute network-based Git commands as shown in SKILL.md and scripts/run.sh.
  • Sanitization: Documentation in references/audit.md highlights a security auditor with static and dataflow analysis capabilities to mitigate risks.
Recommendations
  • HIGH: Downloads and executes remote code from: https://raw.githubusercontent.com/runkids/skillshare/main/skills/skillshare/scripts/run.sh - DO NOT USE without thorough review
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Oct 6, 2026, 04:20 PM