image-upscaling
Fail
Audited by Gen Agent Trust Hub on Feb 19, 2026
Risk Level: CRITICALREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- REMOTE_CODE_EXECUTION (CRITICAL): The file SKILL.md contains a 'Quick Start' instruction to run 'curl -fsSL https://cli.inference.sh | sh'. This pattern is a confirmed remote code execution vector from an untrusted source.
- EXTERNAL_DOWNLOADS (HIGH): The skill relies on and installs software from 'inference.sh', which is not a recognized 'Trusted External Source'.
- COMMAND_EXECUTION (MEDIUM): The skill is configured to allow any 'infsh' command via the Bash tool (allowed-tools: Bash(infsh *)), which could be abused if the binary contains vulnerabilities or hidden features.
- PROMPT_INJECTION (LOW): The skill processes untrusted data via the 'image_url' parameter. Evidence Chain: (1) Ingestion points: 'image_url' in SKILL.md tool calls. (2) Boundary markers: Absent. (3) Capability inventory: Subprocess calls via 'infsh' across all operations. (4) Sanitization: Absent.
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