Results for “command-guard”

54 skills

Safety guardrails for destructive commands. (gstack)

Destructive Command Guard. Installs a pre-tool-use hook that blocks unrecoverable shell commands (rm -rf /, git reset --hard, git clean -fd, rm of .env / credentials, force-pushing to main, fork bombs, shred / dd, etc.) before the agent executes them. Use when the user says "install dcg", "destructive command guard", "guard rails for destructive commands", or invokes /dcg.

Full safety mode: destructive command warnings + directory-scoped edits. (gstack)

Full safety mode: destructive command warnings + directory-scoped edits. (gstack)

Full safety mode: destructive command warnings + directory-scoped edits. (gstack)

Prevents destructive operations when working on production systems or running agents autonomously by intercepting risky commands and restricting file edits to a specified directory.

More results

Prevents destructive operations on production systems and restricts edits to a specified directory when running agents autonomously.

Prevents destructive operations on production systems and restricts file edits to a specific directory when running agents autonomously.

Use this skill to prevent destructive operations when working on production systems or running agents autonomously.

Scan untrusted external text (web pages, tweets, search results, API responses) for prompt injection attacks. Returns severity levels and alerts on dangerous content. Use BEFORE processing any text from untrusted sources.

Forces AI agents to investigate before editing or running destructive commands, improving code quality by requiring concrete facts like importers, data schemas, and user instructions.

Defending Llms With Guardrails

Deploy Llama Guard, NeMo Guardrails, and LLM Guard as runtime input/output scanners to block jailbreaks, prompt injection, and toxic content in production LLM applications.

24.6k · bundle

Keeps long AI sessions on track by tracking decisions, detecting scope creep, and flagging drift before it costs work.

Full safety mode: destructive command warnings + directory-scoped edits. Combines /careful (warns before rm -rf, DROP TABLE, force-push, etc.) with /freeze (blocks edits outside a specified directory). Use for maximum safety when touching prod or debugging live systems. Use when asked to "guard mode", "full safety", "lock it down", or "maximum safety". (gstack)

Bash Pipeline Analysis

Safety guardrails for destructive commands. Warns before rm -rf, DROP TABLE, force-push, git reset --hard, kubectl delete, and similar destructive operations. User can override each warning. Use when touching prod, debugging live systems, or working in a shared environment. Use when asked to "be careful", "safety mode", "prod mode", or "careful mode". (gstack)

Security Guardian

Resolves legacy references to the security-guardian capability by routing to the current runtime equivalent.

Blocks Edit/Write/Bash actions until the agent presents concrete facts about imports, data schemas, and the user's instruction, improving output quality.

Run a command inside a running Docker container

Enforces a read-only rule for filesystem junctions and symlinks, blocking writes, deletes, and git commits that resolve outside the current project root.

Fact-forcing gate that blocks Edit/Write/Bash (including MultiEdit) and demands concrete investigation (importers, data schemas, user instruction) before allowing the action. Measurably improves output quality by +2.25 points vs ungated agents.

Meta's 86M prompt injection and jailbreak detector. Filters malicious prompts and third-party data for LLM apps. 99%+ TPR, <1% FPR. Fast (<2ms GPU). Multilingual (8 languages). Deploy with HuggingFace or batch processing for RAG security.

GPG (GNU Privacy Guard) encryption and signing reference. Covers key generation (Ed25519/RSA), export/import, keyservers, file encryption (symmetric + asymmetric), git commit signing, detached signatures, gpg-agent caching, SSH via GPG, and pass password manager.

Fact-forcing gate that blocks Edit/Write/Bash (including MultiEdit) and demands concrete investigation (importers, data schemas, user instruction) before allowing the action. Measurably improves output quality by +2.25 points vs ungated agents.

GPG (GNU Privacy Guard) encryption and signing reference. Covers key generation (Ed25519/RSA), export/import, keyservers, file encryption (symmetric + asymmetric), git commit signing, detached signatures, gpg-agent caching, SSH via GPG, and pass password manager.

orchestra-research

Detect prompt injections and jailbreak attempts in LLM applications using Meta's 86M parameter classifier. Filter user inputs, third-party data, and RAG documents with low latency and multilingual support.

Secure Code Guardian

Guides implementing authentication, authorization, input validation, and OWASP Top 10 prevention with secure code patterns and validation checkpoints.

10.4k · bundle

Modal Function List

List deployed Modal functions in the current workspace

Start a stopped Docker container by name or ID

Sam Monitor Builder

Create a SAM.gov search monitor from a pursuit or expiring row — persists to Pipeline and writes sam_monitor.md in the pursuit folder. Primary admin rote task for capture managers watching recompetes.

Skill Stocktake

用于审计Claude技能和命令的质量。支持快速扫描（仅变更技能）和全面盘点模式，采用顺序子代理批量评估。

Send an HTTP POST to any configured webhook endpoint

Meta's 86M prompt injection and jailbreak detector. Filters malicious prompts and third-party data for LLM apps. 99%+ TPR, <1% FPR. Fast (<2ms GPU). Multilingual (8 languages). Deploy with HuggingFace or batch processing for RAG security.

netanel-abergel

Pre Commit Guard

Runs before every git commit on heleni-memory. Checks: no credentials in tracked files, no oversized files, valid SKILL.md frontmatter for any new/modified skill. Triggers: "commit", "before push", "validate repo", or auto-runs as a git pre-commit hook.

Fact-forcing gate that blocks Edit/Write/Bash (including MultiEdit) and demands concrete investigation (importers, data schemas, user instruction) before allowing the action. Measurably improves output quality by +2.25 points vs ungated agents.

Stop a running Docker container gracefully