higgsfield-generate

Fail

Audited by Snyk on May 5, 2026

Risk Level: CRITICAL
Full Analysis

CRITICAL E005: Suspicious download URL detected in skill instructions.

  • Suspicious download URL detected (high risk: 0.90). This is higher-risk because it is a direct link to a shell installer (.sh) served from raw.githubusercontent.com and the skill explicitly instructs using curl | sh to execute it remotely—running an unreviewed script can execute arbitrary code even if hosted on GitHub, so verify the repo, maintainers, and contents before running.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.90). The skill's Marketing Studio workflows (e.g., "higgsfield marketing-studio products fetch --url " and the Click-to-Ad shortcut) explicitly fetch and ingest arbitrary public product URLs and then use that imported content as inputs to generation, so untrusted third‑party web content can directly influence generation and tool actions.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

  • Potentially malicious external URL detected (high risk: 0.90). The skill's bootstrap step instructs running a remote installer that is fetched-and-executed at runtime via "curl -fsSL https://raw.githubusercontent.com/higgsfield-ai/cli/main/install.sh | sh", which directly executes external code and is required for the skill to run.

Issues (3)

E005
CRITICAL

Suspicious download URL detected in skill instructions.

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

W012
MEDIUM

Unverifiable external dependency detected (runtime URL that controls agent).

Audit Metadata
Risk Level
CRITICAL
Analyzed
May 5, 2026, 10:42 AM
Issues
3
Security Audit — snyk — higgsfield-generate