workflow/workflow vercel | | The skill actively promotes arbitrary code execution and command injection | 2.0k | 2.0k | 8 | 100Critical |
skills/agent-tools tool-belt | | The skill allows remote code execution, | 414 | – | 8 | 100Critical |
skills/tavily-dynamic-search tavily-ai | | This skill enables remote code execution via `curl | bash | 270 | 2.0k | 5 | 100Critical |
skills/tavily-search tavily-ai | | The Tavily search skill allows remote code execution and arbitrary file writes, enabling system compromise and data exfiltration. | 270 | 15.5k | 2 | 100Critical |
skills/tavily-extract tavily-ai | | The skill allows remote code execution via `curl | 270 | 5.9k | 6 | 100Critical |
batterie-de-savoir/update spm1001 | | This skill executes arbitrary code and installs malicious packages via | 2 | – | 10 | 100Critical |
flash-list/agent-device shopify | | The skill executes shell commands and mandates `adb` for | 7.1k | 9 | 2 | 100Critical |
second-brain-skills/para-manager shestera | | The skill allows command injection and | 0 | 1 | 4 | 100Critical |
opc-skills/requesthunt resciencelab | | This skill is dangerous as it can download and execute | 838 | 1.2k | 3 | 100Critical |
model-deployment pluginagentmarketplace | | The model deployment skill allows remote code execution and uses unpinned dependencies, posing significant supply chain risks. | 2 | 5 | 2 | 100Critical |
prelude-claude-plugin/nist preludeorg | | This skill is highly vulnerable to command injection and | 0 | – | 7 | 100Critical |
overthink-plugins/generate overthinkos | | This skill generates Containerfiles but introduces supply chain vulnerabilities | 0 | – | 4 | 100Critical |
overthink-plugins/layer overthinkos | | This skill allows arbitrary command execution, privilege escalation | 0 | – | 6 | 100Critical |
harness-design/harness-design zanwei | | This skill allows command injection, arbitrary | 1 | 2 | 6 | 100Critical |
prose/open-prose openprose | | This skill self-modifies the agent's memory | 1.2k | 1.1k | 14 | 100Critical |
skills/sentry openai | | The skill enables remote code execution and command injection | 18.3k | 951 | 5 | 100Critical |
skills/render-deploy openai | | The skill downloads and executes remote code, allowing arbitrary code execution and potential system compromise. | 18.3k | 909 | 1 | 100Critical |
ui-ux-pro-max-skill/ui-ux-pro-max nextlevelbuilder | | The skill is vulnerable to command injection via user input and | 74.5k | 148.3k | 3 | 100Critical |
architecture-cowork-plugin/architecture-methodology navraj007in | | This skill executes shell commands, handles sensitive API | 2 | – | 9 | 100Critical |
codex-collab/codex-collab masuP9 | | This skill allows arbitrary command execution and privilege escalation via user | 2 | – | 6 | 100Critical |
design-extract/extract-design manavarya09 | | The skill allows arbitrary command execution via user | 2.2k | 1.1k | 3 | 100Critical |
deepagentsjs/langsmith-trace langchain-ai | | The skill downloads and executes remote code, and encourages risky inferences when environment variables are missing. | 1.2k | 21 | 2 | 100Critical |
ctf-skills/ctf-pwn ljagiello | | This skill is an exploitation toolkit enabling arbitrary | 1.9k | 3.0k | 9 | 100Critical |
ctf-skills/ctf-misc ljagiello | | This CTF skill details numerous | 1.9k | 2.9k | 16 | 100Critical |
spacemolt-docs/spacemolt kongyo2 | | The skill executes arbitrary remote code via `npx`, | 0 | – | 8 | 100Critical |
nano-banana-2-skill/nano-banana kingbootoshi | | The skill executes arbitrary remote code from external sources | 368 | 400 | 6 | 100Critical |
langsmith-skills/langsmith-dataset langchain-ai | | This skill executes arbitrary remote code, exfiltrates | 111 | 1.6k | 9 | 100Critical |
langsmith-skills/langsmith-evaluator langchain-ai | | The Langsmith Evaluator skill downloads and executes remote code, enabling arbitrary code | 111 | 1.6k | 1 | 100Critical |
ilo/ilo ilo-lang | | This skill enables arbitrary command execution, command injection | 0 | – | 6 | 100Critical |
adb-android-control hah23255 | | This skill grants an AI agent complete control over | 1 | – | 24 | 100Critical |
jules-skills/automate-github-issues google-labs-code | | This skill enables arbitrary code execution, downloads remote scripts, | 52 | – | 6 | 100Critical |
awesome-copilot/winmd-api-search github | | The skill executes local PowerShell scripts with user | 32.2k | 5.4k | 4 | 100Critical |
awesome-copilot/containerize-aspnetcore github | | The skill generates Dockerfiles with multiple command injection vectors, | 32.2k | 8.4k | 8 | 100Critical |
skills/security-review getsentry | | This skill enables arbitrary shell command execution and extensive file | 668 | 4.7k | 7 | 100Critical |
sentry-python/security-review getsentry | | This skill can execute arbitrary shell | 2.2k | 18 | 6 | 100Critical |
oh-my-agent/oma-dev-workflow first-fluke | | The skill installs `mise` via `curl | | 906 | 9 | 11 | 100Critical |
developing-genkit-dart firebase | | This skill downloads and executes remote code, misrepresenting itself | 249 | 27.3k | 2 | 100Critical |
agent-skills/developing-genkit-dart firebase | | The skill enables remote code download and execution, allowing arbitrary code execution and potential compromise of the agent. | 268 | 40.8k | 1 | 100Critical |
sulcus/openclaw-sulcus-skill digitalforgeca | | The skill allows shell command execution, ex | 0 | – | 7 | 100Critical |
xreview/xreview davidleitw | | The skill allows remote code execution, enables prompt injection | 12 | – | 11 | 100Critical |
claude-plugin/code-review coderabbitai | | This skill performs remote code execution, ex | 43 | 13 | 3 | 100Critical |
agent-skills/clickhousectl-local-dev clickhouse | | The skill allows remote code execution and is vulnerable to command injection via unsanitized user input in `clickhousectl` commands. | 415 | 336 | 2 | 100Critical |
skills/clerk-backend-api clerk | | The skill executes unverified remote code from | 40 | 4.1k | 4 | 100Critical |
skills/brightdata-cli brightdata | | This skill enables remote code execution | 114 | 1.6k | 5 | 100Critical |
brave-search-skills/bx brave | | The skill enables remote code download and execution, posing a | 125 | 84 | 2 | 100Critical |
agent-skills/github-navigator arshia2114 | | This skill grants broad `Bash(gh:*)` | 0 | – | 9 | 100Critical |
crabshell/verifying ZipperBagCoffee | | This skill allows arbitrary command execution and | 1 | – | 15 | 100Critical |
pix-ai-coding-assistant/exploits-search Vulnetix | | This offensive security tool installs a CLI from external sources | 4 | – | 7 | 100Critical |