common-llm-security Eval report.

Task wording matches this skill metadata.

• Evaluate common-llm-security before installing it in an agent workflow
• security
• RAG and knowledge workflows; Claude Code teams; teams that value GitHub adoption signals

Install handoff is available.

• npx skills add HoangNguyen0403/agent-skills-standard --skill common-llm-security

standard package or runtime install path

• npx skills add HoangNguyen0403/agent-skills-standard --skill common-llm-security

Good trust signals with a few areas worth checking before rollout.

• Strong shortlist
• 559 GitHub stars
• MIT

Needs review

• Dependency or permission surface needs review

This skill should not be selected by an agent without explicit human security review.

• Do not auto-install. Inspect the source, dependencies, and permission surface first.
• Metadata combines secrets access with shell or command execution

MIT

• MIT

secrets or environment access, shell or command execution

• Shell or command execution: high
• Network access: medium
• Secrets or environment access: high