The Agent Skills Directory

[DATA_EXFILTRATION]: The skill performs network requests to an external API endpoint to retrieve search results.
Evidence: scripts/search.mjs uses the fetch API to communicate with https://api.valyu.ai/v1/search.
Context: This network access is the primary intended function of the skill for querying the DrugBank database.
[INDIRECT_PROMPT_INJECTION]: The skill ingests and processes drug information and mechanism data from an external API, which could contain instructions intended to influence the agent's behavior.
Ingestion points: Data is retrieved from the api.valyu.ai endpoint in scripts/search.mjs.
Boundary markers: None are implemented; results are returned directly to the agent in JSON format.
Capability inventory: The skill has the ability to perform network requests (fetch) and write configuration data to the file system (~/.valyu/config.json).
Sanitization: No sanitization, filtering, or instruction-blocking delimiters are applied to the content or results fields received from the API.
[COMMAND_EXECUTION]: The skill utilizes a bash wrapper to invoke a Node.js CLI script, passing user-provided arguments.
Evidence: scripts/search executes node "${SCRIPT_DIR}/search.mjs" "$@".
Path Resolution: The skill provides instructions for the agent to dynamically locate the script path using the find command, which is a standard procedure for local script execution in this environment.

drugbank-search