Skills
skills/antithesishq/antithesis-skills/antithesis-workload/Gen Agent Trust Hub

antithesis-workload

Pass

Audited by Gen Agent Trust Hub on May 5, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides instructions for a legitimate software development and testing workflow. It utilizes vendor-owned tools and documentation and contains no evidence of malicious intent.- [PROMPT_INJECTION]: The skill defines a workflow for processing external property catalogs and evidence files to generate test code. This establishes an indirect prompt injection surface as it ingests untrusted data that influences code generation. \n
  • Ingestion points: antithesis/scratchbook/property-catalog.md and property evidence files in SKILL.md.\n
  • Boundary markers: None identified.\n
  • Capability inventory: File generation in antithesis/test/ and execution of snouty validate.\n
  • Sanitization: None described.- [COMMAND_EXECUTION]: The skill involves generating and validating test commands and using the snouty CLI. These operations are within the expected scope of a testing and workload implementation tool.
Audit Metadata
Risk Level
SAFE
Analyzed
May 5, 2026, 11:15 PM