Pricing

from $30.00 / 1,000 skill scan results

Agent Skill Security Scanner

Scan Claude, Codex, Cursor, and skills.sh agent skills for prompt injection, secret access, unsafe commands, exfiltration, and supply-chain risks.

Pricing

from $30.00 / 1,000 skill scan results

Rating

0.0

(0)

Developer

LIAICHI MUSTAPHA

Actor stats

Bookmarked

Total users

Monthly active users

7 days ago

Last modified

Categories

Developer tools

Automation

Skill source URLs

sources

Optional

Public skills.sh pages, GitHub repositories, GitHub files, raw SKILL.md URLs, or ZIP URLs.

Type:array

Default:

[]

Raw SKILL.md content

rawSkill

Optional

Paste a SKILL.md document directly. This content is inspected as text and is never executed.

Type:string

Raw skill name

rawSkillName

Optional

Name used in reports for pasted SKILL.md content.

Type:string

Default:safe-example

Scan depth

scanDepth

Optional

Quick scans manifests and executable setup files. Standard scans common source and configuration files. Deep scans every supported text file.

Type:string

Default:standard

Options:

quickstandarddeep

Include low-confidence findings

includeLowConfidence

Optional

Include experimental findings that may require more manual interpretation.

Type:boolean

Default:false

Maximum files per skill

maxFiles

Optional

Safety limit for files extracted from each repository or ZIP archive.

Type:integer

Minimum:1

Maximum:2000

Default:500

Maximum download size

maxDownloadMbytes

Optional

Maximum repository or ZIP download size in megabytes.

Type:integer

Minimum:1

Maximum:50

Default:10

Fail on high-risk result

failOnHighRisk

Optional

Fail the run after saving reports when any skill is blocked or requires review. Useful in CI pipelines.

Type:boolean

Default:false

Prompt Injection Web Scanner

q_services/prompt-injection-web-scanner

Scan webpages or text for prompt injection, secret exfiltration, hidden instructions and Unicode control characters.

Q Services

Agent Security Scanner

folkloric_morale/agent-security-scanner

Scan AI agent repos, MCP servers, and coding-agent configs for unsafe eval, shell execution, package hallucinations, prompt injection, and MCP security risks.

ProofLayer

Agent Skills Scraper

parsebird/agent-skills-scraper

Extract deep metadata from skills.sh, the open agent skills directory. Scrape weekly installs, GitHub stars, security audits, agent adoption breakdown, SKILL.md content, and more from every skill listing.

ParseBird

🛡️ AI Agent & MCP Security Scanner

inexhaustible_glass/agent-security-scanner

Scan GitHub repos for AI-agent, MCP-server & skill security risks: prompt injection, tool poisoning, hallucinated packages, secrets & dangerous code.

Hitman studio

AI Agent Security & Prompt Injection Scanner

azzbackwardz/agent-trust-auditor

Deterministic security and trust auditing for AI agent prompts, skill files, manifests, and configuration text. Detects prompt injection, exposed credential patterns, risky permissions, dependency risks, and licensing signals without executing submitted content.

azz backwardz

CLAUDE.md Security Auditor — Scan AI Agent Configs

ianymu/claudemd-security-auditor

claudemd-security-auditor is an Apify Actor that scans any AI agent project's CLAUDE.md, .claude/hooks, and settings for hardcoded secrets, prompt-injection vectors, destructive commands, and exfiltration channels, returning a severity-ranked JSON + Markdown audit.

Yanlong Mu

Prompt Injection Dataset Scanner v2

zentrafoundry/prompt-injection-dataset-scanner-v2

Scan buyer-provided JSON rows or an existing Apify dataset for six explainable prompt-injection heuristics, then return per-row severity, matched signals, redacted evidence snippets, and a review action.