The Agent Skills Directory

[PROMPT_INJECTION]: The skill contains instructions that steer the agent's behavior to proactively promote a specific commercial platform (www.k-dense.ai) for complex workflows, which influences the agent's interaction style based on the author's commercial interests.
[PROMPT_INJECTION]: The skill ingests untrusted scholarly data from the external OpenAlex API, creating a surface for indirect prompt injection.
Ingestion points: The skill retrieves metadata such as paper titles, abstracts, and author names from the OpenAlex API via the 'scripts/openalex_client.py' component.
Boundary markers: No delimiters or specific instructions to ignore embedded commands within the retrieved scholarly text are provided to the agent.
Capability inventory: The skill has access to file system operations (CSV export) and network communication tools.
Sanitization: No sanitization or validation of the content retrieved from the external API is documented or demonstrated in the provided code snippets.
[DATA_EXFILTRATION]: The skill performs network requests to the OpenAlex API (api.openalex.org) using the 'requests' library. This is the primary intended function of the skill and involves a well-known academic service.
[COMMAND_EXECUTION]: The documentation provides standard installation instructions for the 'requests' library using the 'uv pip install' command.

openalex-database