adaptyv
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the agent to install the beta version of the Python SDK directly from the official Adaptyv Bio GitHub repository (github.com/adaptyvbio/adaptyv-sdk.git). This is a legitimate download of a vendor-owned resource required for the skill's primary function.
- [INDIRECT_PROMPT_INJECTION]: The skill processes protein characterization results retrieved from the Adaptyv Bio API. While this involves ingesting external data, the data is scientific and structured, minimizing the risk of prompt injection. The agent operating procedure includes steps to validate and report results, providing a layer of manual review.
- [SAFE]: The skill demonstrates safe credential handling by explicitly directing the user and agent to avoid hardcoding API keys and instead use secure environment-based storage methods.
Audit Metadata