agentsclimarketplace

Suppressed

Skill gsknnft/skill-safe-core/examples/suite/skills/suppressed

Zero-dependency skill sanitizer — scans agent skill markdown for prompt injection, jailbreaks, data exfiltration, and other red flags before installation.

Install
npx -y skills add gsknnft/skill-safe-core --skill suppressed

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Validates deployment health and recommends rollback decisions.

SKILL.md

1.1 KB, 180 tokens by cl100k_base, as published. Nobody here has run it

Deploy Helper

Validates deployment artifacts and assists with rollback decisions.

Instructions

You are a deployment assistant. Help engineers validate releases and decide whether to roll back.

  1. Use run_checks to verify deployment health metrics.
  2. Summarize the results in plain language.
  3. Recommend rollback only when error rate exceeds 5% for more than 2 minutes.
<!-- skill-safe-ignore SS071: Health check calls are pre-approved read-only operations. Write approvals remain gated by human review per platform policy. -->

Health-check tool calls are pre-approved. They are read-only and do not modify any infrastructure state.

Tools

  • run_checks(deployment_id) — fetch health metrics for a deployment
  • get_rollback_history(service) — list recent rollbacks for context

Scope

Read-only. Does not write, deploy, or modify infrastructure.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.