antithesis-launch

Pass

Audited by Gen Agent Trust Hub on May 9, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes shell commands including docker compose build, snouty validate, and snouty run as part of its core functionality to launch Antithesis tests.
  • [EXTERNAL_DOWNLOADS]: The skill references documentation and installation instructions from the vendor's official GitHub repository at github.com/antithesishq/snouty.
  • [INDIRECT_PROMPT_INJECTION]: The skill exhibits a potential surface for indirect prompt injection as it reads local files to determine configuration.
  • Ingestion points: Reads content from AGENTS.md, README*, Makefile*, and docker-compose.yaml (SKILL.md).
  • Boundary markers: None identified in the instructions.
  • Capability inventory: Executes shell commands (docker compose, snouty) based on findings (SKILL.md).
  • Sanitization: No specific sanitization or validation of the file content before use in commands is mentioned.
Audit Metadata
Risk Level
SAFE
Analyzed
May 9, 2026, 07:00 PM