100Critical
The skill insecurely executes unverified remote code via direct shell piping, granting external servers arbitrary control over the agent's environment without integrity checks or version pinning.
HygienePackaging & Manifest1 finding
Skill Info
Namehiggsfield-ai/skills/higgsfield-soul-id
Registrygithub
Version7c04e10f8a60
PURLpkg:github/higgsfield-ai/skills@7c04e10f8a60?skill=higgsfield-soul-id
Stars492
Installs57,800
Source
Install
This skill has been flagged as potentially malicious. Review the findings below before installing.
GitHub
57,800 installs
Skills.shDocs
npx skills add https://github.com/higgsfield-ai/skillsAssessments (3)
AI Agent Traps ↗Remote code download and execution detectedcriticalremote execAML.T0050AML.T0053AML.T0072LLM05:2025LLM06:2025
Remote code download and execution detected
95% confidenceline 29
curl -fsSL https://raw.githubusercontent.com/higgsfield-ai/cli/main/install.sh | sh
A remote resource is downloaded with curl/wget and piped directly into a shell interpreter (optionally via sudo). The downloaded script runs with no integrity check (no checksum/signature), so a compromised server, MITM, or hijacked URL leads to arbitrary code execution. Download to a file, verify it (e.g. sha256sum -c against a pinned digest, or a signature), then execute it.criticalvulnAML.T0050AML.T0053AML.T0072LLM05:2025LLM06:2025
A remote resource is downloaded with curl/wget and piped directly into a shell interpreter (optionally via sudo). The downloaded script runs with no integrity check (no checksum/signature), so a compromised server, MITM, or hijacked URL leads to arbitrary code execution. Download to a file, verify it (e.g. sha256sum -c against a pinned digest, or a signature), then execute it.
95% confidenceline 1
curl -fsSL https://raw.githubusercontent.com/higgsfield-ai/cli/main/install.sh | sh
Implicit trust in external binarymediumsupply chainAML.T0010AML.T0019AML.T0058LLM03:2025
The skill forces the installation of an external binary from a remote URL without version pinning or integrity verification, effectively granting the remote server control over the agent's execution environment. [ensemble: confirmed by 3/3 passes; severity set to the agreed median (ADR-0067).]
95% confidenceline 29
curl -fsSL https://raw.githubusercontent.com/higgsfield-ai/cli/main/install.sh | sh
Missing licenseinfopolicy violation
Skill does not specify a license field. Specifying a license helps users understand usage terms.
100% confidence
Version History (2)
Badge
Markdown
[](https://mondoo.com/ai-agent-security/skills/github/higgsfield-ai/skills/higgsfield-soul-id)HTML
<a href="https://mondoo.com/ai-agent-security/skills/github/higgsfield-ai/skills/higgsfield-soul-id"><img src="https://mondoo.com/ai-agent-security/api/badge/github/higgsfield-ai/skills/higgsfield-soul-id.svg" alt="Mondoo Skill Check" /></a>Image URL
https://mondoo.com/ai-agent-security/api/badge/github/higgsfield-ai/skills/higgsfield-soul-id.svgSecure your AI agents
Skills can read files, run commands, and access credentials. Mondoo helps organizations manage the security risks of AI agent skills across their entire fleet.
- Continuous scanning of skills across all registries
- Policy enforcement before skills reach your agents
- Integration with your existing security workflow