AgentSidekick

hardstop

Pluginby frmorettoHEU

Don't let AI destroy your hard work! HardStop is a rock-solid protection for AI-generated commands. Pre-execution safety validation for Claude Code, Claude Cowork. Catches dangerous commands before they run: whether from AI mistakes, hallucinations, prompt injection, or misunderstood instructions. Seatbelts for the agentic AI era.

SRC Publisher-stated: these are the publisher's own words, not an assessment.

RepositorySource listing

Key facts

Type
Plugin · claude-pluginSRC
Publisher
frmoretto · individualSRC
Licence
Unknown
Open source
Unknown
Hosting
Unknown
Latest version
Unknown
Languages
pythonSRC
First published
SRC
In this catalogue since
DER
Last verified
Not verified by a researcher. Last seen in a source on 2026-11-21.

Capabilities and categories

Assigned by keyword rules from the description unless marked otherwise. The matched word is shown so you can judge the match.

CapabilityEvidenceKind
Agent Threat Protectionmatched prompt injectionDER
Agent Skills & Pluginsmatched claude code hooksDER
Digital Marketplacesmatched plugin marketplaceDER
Prompt Injection Defensematched prompt injectionDER

Filed underAgent InfrastructureDeveloper ToolsAI Coding AgentsAgent CommerceAgent SecurityAgent Payments & MonetizationCoding Agent CLIs & Extensions

Integrations DER

No third-party service is named in the description or package metadata.

Platform compatibility

No pairing has been tested by AgentSidekick. Each status says what kind of evidence exists, not whether it works for you.

Vendor claimed1
PlatformBasis
Claude CodeThe publisher's description names Claude Code. A claim by the vendor; not independently tested.
Unknown46

Could not confirm whether Each platform listed supports Claude plugins.

Install

Read from registry metadata. Follow the publisher's instructions; we have not run this.

No install information

No package, remote endpoint, install link or documentation link appears in any source for this product.

The repository may carry instructions in its README.

Permissions and signals

Signals, not a safety verdict. They describe what the product's metadata references. Security review: not reviewed.

No signals collected

Automated inspection found nothing to report, or there was no metadata to inspect. That is not evidence of safety.

Known advisories for the published package SRC

An advisory existing does not mean the listed version is affected: compare the vulnerable range with the version you install. None found is not evidence of safety.

No advisories found

No published advisory matches a package this product declares. Products without a declared package cannot be matched at all. This is not evidence of safety.

Evaluation

Separate dimensions, each with its evidence. There is no overall score: the dimensions do not add up to one number honestly.

Source authority

Auto-discovered

Found through repository metadata; type and categories are inferred, not confirmed.

Publisher verification

Not verified

No publisher identity check is available for this source.

Maintenance activity

Slowing

Last push 2026-04-18.

Licence clarity

No licence detected

GitHub did not detect a standard licence file. Without one, default copyright applies.

Installation clarity

Unknown

No install information in any source.

Documentation

Repository / website only

No dedicated documentation URL on record. AgentSidekick has not assessed documentation quality.

Compatibility evidence

Vendor claimed

The publisher names 1 platform(s). None independently tested.

Security review

Not reviewed

AgentSidekick has not audited this product. No automated signals were collected. That is not evidence of safety.

Pricing

Not published in any source we track.

Repository activity

frmoretto/hardstop. Read from the GitHub API on 2026-11-21.

32SRCGitHub stars
2SRCForks
1SRCOpen issues
7mo agoSRCLast push2026-04-18
v1.4.9SRCLatest release2026-04-18

Version history SRC

No version list is published in any source we track.

Change history

What changed between two ingests of the same source, and when the product was first seen. Registry releases are under Version history.

  1. First seen

Competitors and alternativesDER

Paired by shared capabilities and integrations. Similar on paper; not tested side by side.

Direct

Same type, overlapping capabilities.

SharesAgent Skills & PluginsDigital Marketplaces

Adjacent

A different form or a partial overlap.

skills-janitor

Agent skillby khendzelHEU

139 GitHub starspushed 1mo agoMIT

SharesAgent Skills & PluginsAgent Threat ProtectionPrompt Injection Defense

mastyf.ai

MCP serverby mastyf-aiSRC

22 GitHub starspushed todayAGPL-3.0

SharesAgent Threat ProtectionPrompt Injection Defense

SharesAgent Threat ProtectionPrompt Injection Defense

vigil-llm

Infrastructureby deadbitsHEU

511 GitHub starspushed 2y agoApache-2.0

SharesAgent Threat ProtectionPrompt Injection Defense

SharesAgent Threat ProtectionPrompt Injection Defense

buildwithclaude

MCP serverby davepoonHEU

3.8k GitHub starspushed 1d agoMIT

SharesAgent Skills & PluginsDigital Marketplaces

Provenance

Which source set each field, what kind of claim it is, and when.

FieldSourceKindSet on
Canonical URLGitHub topic searchSRC2026-11-21
PublisherGitHub topic searchSRC2026-11-21
DescriptionGitHub topic searchSRC2026-11-21
Integration typeGitHub topic searchSRC2026-11-21
LanguagesGitHub repository metadataSRC2026-11-21
NameGitHub topic searchSRC2026-11-21
TypeGitHub topic searchSRC2026-11-21
PublishedGitHub topic searchSRC2026-11-21
RepositoryGitHub topic searchSRC2026-11-21
Source URLGitHub topic searchSRC2026-11-21

Sources

Not verified by a researcher. Last seen in a source on . Report incorrect information

Page data last updated .