product-changelog
Fail
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: CRITICALREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- REMOTE_CODE_EXECUTION (CRITICAL): The skill contains the command
curl -fsSL https://cli.inference.sh | sh. This pattern downloads a script from a remote server and pipes it directly into the shell for execution without integrity verification, which is a classic vector for immediate system compromise. - EXTERNAL_DOWNLOADS (HIGH): The skill relies on an external CLI tool (
infsh) and additional skills fetched vianpxfrom theinferenceshorganization, neither of which are on the trusted source list. - COMMAND_EXECUTION (MEDIUM): The skill utilizes a custom binary (
infsh) and is granted broad shell execution permissions via theallowed-tools: Bash(infsh *)configuration. - PROMPT_INJECTION (LOW): The skill ingests user-provided text for changelog generation and image prompts, creating a surface for indirect prompt injection. Ingestion points: User-controlled strings used in
infsh app runinputs. Boundary markers: Absent. Capability inventory: Full subprocess execution via theinfshCLI. Sanitization: No evidence of input escaping or validation.
Recommendations
- HIGH: Downloads and executes remote code from: https://cli.inference.sh - DO NOT USE without thorough review
- AI detected serious security threats
Audit Metadata