antithesis-launch

Pass

Audited by Gen Agent Trust Hub on May 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes shell commands using docker compose and the snouty CLI to build project artifacts and launch test runs.
  • [EXTERNAL_DOWNLOADS]: The skill references documentation and installation scripts from the official Antithesis GitHub repository (github.com/antithesishq/snouty).
  • [PROMPT_INJECTION]: The skill contains an indirect prompt injection surface as it processes local repository files to determine its configuration.
  • Ingestion points: The skill inspects AGENTS.md, README files, Makefiles, and docker-compose.yaml to identify the harness layout and configuration directory.
  • Boundary markers: No explicit delimiters or boundary markers are used when interpolating discovered repository content into internal prompts.
  • Capability inventory: The skill possesses command execution capabilities via docker and snouty.
  • Sanitization: No explicit sanitization of repository content is defined before the data is used in command construction.
Audit Metadata
Risk Level
SAFE
Analyzed
May 15, 2026, 07:02 PM
Security Audit — agent-trust-hub — antithesis-launch