agent-tools

Pass

Audited by Gen Agent Trust Hub on Mar 25, 2026

Risk Level: SAFEREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The skill provides instructions to download and execute an installation script directly from https://cli.inference.sh using a pipe-to-shell pattern.
  • [EXTERNAL_DOWNLOADS]: The skill fetches platform-specific binaries, manifest files, and SHA-256 checksums from dist.inference.sh for manual installation and updates.
  • [COMMAND_EXECUTION]: The skill relies on the infsh CLI tool to perform operations such as running AI apps, authenticating users, and managing task states. Access is scoped to the infsh command via the allowed-tools configuration.
  • [INDIRECT_PROMPT_INJECTION]: The skill accepts external data as input for AI models, which could potentially contain malicious instructions.
  • Ingestion points: Data provided via the --input flag in infsh app run commands, either as JSON strings or file paths.
  • Boundary markers: No specific delimiters or instructions to ignore embedded commands are used when passing data to the CLI.
  • Capability inventory: Shell execution of the infsh tool for processing AI tasks.
  • Sanitization: Input data is passed directly to the CLI tool without explicit sanitization or validation within the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 25, 2026, 01:02 AM