higgsfield-generate
Fail
Audited by Snyk on Aug 8, 2026
Risk Level: CRITICAL
Full Analysis
CRITICAL E005: Suspicious download URL detected in skill instructions.
- Suspicious download URL detected (high risk: 1.00). The skill instructs users to curl and pipe a raw GitHub-hosted install.sh (https://raw.githubusercontent.com/higgsfield-ai/cli/main/install.sh) and execute it, which is a direct remote shell script fetch-and-run — a high-risk pattern for distributing malware.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). The skill’s required runtime path is executing the Higgsfield CLI based on user prompt/media inputs (e.g.,
higgsfield generate create … --prompt ... --waitandhiggsfield generate workflow ... --video/--sketch/--prompt --wait), so outsider-authored free text from the user is directly ingested as the--promptargument.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 1.00). The bootstrap step runs a shell install command that fetches and pipes https://raw.githubusercontent.com/higgsfield-ai/cli/main/install.sh to sh, which executes remote code at runtime and is required if the CLI is not present.
Issues (3)
E005
CRITICALSuspicious download URL detected in skill instructions.
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata