app-store-screenshots

Fail

Audited by Gen Agent Trust Hub on Mar 8, 2026

Risk Level: HIGHEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The skill recommends installing the infsh CLI tool using a piped shell script: curl -fsSL https://cli.inference.sh | sh. While this script originates from the vendor's own domain, the practice of piping remote scripts directly to a shell is inherently risky.
  • [EXTERNAL_DOWNLOADS]: The skill references external binaries and checksums hosted at dist.inference.sh and suggests adding additional skills through the npx package runner.
  • [COMMAND_EXECUTION]: The skill utilizes the Bash tool to execute vendor-specific infsh commands for generating images and videos via various AI models.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it interpolates user-provided text directly into CLI command arguments. (1) Ingestion points: User-defined prompts for image and video generation are passed into the --input flag of the infsh app run command. (2) Boundary markers: No explicit delimiters or instruction-ignore warnings are used to wrap the user input in the examples. (3) Capability inventory: The skill has access to the Bash tool to execute the vendor's CLI. (4) Sanitization: There is no evidence of input validation or sanitization for the user-provided prompts.
Recommendations
  • HIGH: Downloads and executes remote code from: https://cli.inference.sh - DO NOT USE without thorough review
Audit Metadata
Risk Level
HIGH
Analyzed
Mar 8, 2026, 12:34 AM
Security Audit — agent-trust-hub — app-store-screenshots