The Agent Skills Directory

Unverifiable Dependencies & Remote Code Execution (CRITICAL): The skill contains the command curl -fsSL https://cli.inference.sh | sh. This is a piped remote execution from an untrusted source (https://cli.inference.sh) allowing for arbitrary code execution on the host machine.\n- Dynamic Execution (HIGH): The skill uses the infsh tool via bash to run various remote applications (e.g., infsh app run falai/flux-dev-lora). This allows for the runtime execution of unverified applications from an untrusted remote source.\n- Unverifiable Dependencies & Remote Code Execution (MEDIUM): The skill attempts to fetch and install additional components using npx skills add from an unverified repository (inference-sh/skills), which could lead to the execution of malicious code during the addition process.\n- Indirect Prompt Injection (LOW): The skill possesses a surface for indirect prompt injection (Category 8). It ingests untrusted user changelog data and interpolates it into a context that has access to the powerful Bash tool and infsh commands without boundary markers or sanitization. (Ingestion: user-provided changelog details; Boundary: absent; Capability: Bash/infsh; Sanitization: absent).

product-changelog