The Agent Skills Directory

[DATA_EXFILTRATION]: The skill performs network requests to an external API to retrieve patent bibliographic data.
Evidence: The Python script scripts/patent_core_bibliography.py uses urllib.request.urlopen to communicate with the API endpoint specified by the ${NEXSCOPE_PROXY_BASE} environment variable.
Data Handling: Authentication is managed securely through the NEXSCOPE_API_KEY environment variable rather than hardcoded secrets.
[COMMAND_EXECUTION]: The skill executes a Python script to handle parameter processing and API interaction.
Evidence: SKILL.md documents the invocation of python scripts/patent_core_bibliography.py '<JSON params>' [--inline].
[INDIRECT_PROMPT_INJECTION]: The skill represents an ingestion surface for untrusted data retrieved from external patent abstracts and titles.
Ingestion points: Patent metadata including abstractContent, title, and inventors are processed from the API response in scripts/patent_core_bibliography.py.
Boundary markers: The instructions do not explicitly define delimiters to isolate the retrieved patent content from the agent's internal reasoning.
Capability inventory: The skill has network access capabilities and the ability to write JSON files to the local project filesystem (<cwd>/nexscope/).
Sanitization: No explicit sanitization or filtering of retrieved bibliographic text for potential prompt injection payloads is implemented.

ecommerce-patent-core-bibliography