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
Risk Level
CRITICAL
Analyzed
Feb 19, 2026, 01:20 AM