content-creation
Fail
Audited by Snyk on Feb 13, 2026
Risk Level: CRITICAL
Full Analysis
CRITICAL E005: Suspicious download URL detected in skill instructions.
- Suspicious download URL detected (high risk: 0.95). Yes — this is a direct raw GitHub link to an install.sh script from an individual/unknown repo and the skill explicitly instructs piping it to bash (curl | bash), which allows arbitrary code execution and is a high-risk vector for malware.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and executes a remote script from a public third-party URL (curl ... https://raw.githubusercontent.com/esmondo/berkarja/main/scripts/install.sh | bash), so it ingests and runs untrusted content from the open web that could carry injected instructions.
HIGH W008: Secret detected in skill content (API keys, tokens, passwords).
- Attempt to compromise machine state in skill instructions detected (high risk: 1.00). The prompt explicitly instructs running a remote install script via
curl ... | bash, which directs the agent to execute arbitrary code that can modify system files, install software, or create accounts and thus compromises the machine state.
Audit Metadata