antithesis-feature-workload
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill requires the agent to ingest and analyze external assets, such as source code and feature specifications, to create test workloads. This creates a surface for indirect prompt injection if the analyzed content contains adversarial instructions.
- Ingestion points: System Under Test (SUT) source code, design documents, and specifications (SKILL.md, references/feature-analysis.md).
- Boundary markers: The skill does not prescribe specific delimiters or boundary instructions for the ingested SUT content.
- Capability inventory: The agent is instructed to generate test code, build Docker environments, and perform network-based API operations against the SUT (SKILL.md, references/self-driving-workload.md).
- Sanitization: The instructions do not define sanitization procedures for data processed from the SUT.
- [EXTERNAL_DOWNLOADS]: The documentation mentions using vendor-specific tools like the
snoutyCLI and Antithesis SDKs. These are standard components of the Antithesis testing workflow and originate from the skill's authoring organization.
Audit Metadata