The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the user to install the adaptyv-sdk package directly from a GitHub repository rather than a standard registry like PyPI.
Evidence: uv pip install "git+https://github.com/adaptyvbio/adaptyv-sdk.git" in SKILL.md.
[COMMAND_EXECUTION]: The skill provides shell commands for environment setup and package installation.
Evidence: uv pip install, uv add, and curl commands in SKILL.md.
[INDIRECT_PROMPT_INJECTION]: The skill processes data from external sources that could contain malicious instructions.
Ingestion points: Retrieves experiment results, target catalog data, and quotes from the foundry-api-public.adaptyvbio.com API endpoints described in references/api-endpoints.md.
Boundary markers: No explicit delimiters or instructions are provided to the agent to ignore potentially malicious content within sequences, metadata, or result summaries.
Capability inventory: The skill performs network requests to external domains, executes shell commands for installation, and handles experiment submission/retrieval.
Sanitization: There is no mention of sanitization, validation, or schema enforcement for the protein sequence data or API responses before they are processed by the agent.

adaptyv