The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses local scripts (scripts/search and scripts/search.mjs) to interact with the Valyu API. It includes instructions for locating these scripts in the local environment and passing parameters via the command line. All command invocations follow expected patterns for a CLI tool.
[INDIRECT_PROMPT_INJECTION]: The skill processes bioactive molecule data retrieved from the Valyu API. 1. Ingestion points: Data enters the agent's context through the output of the scripts/search command (derived from https://api.valyu.ai/v1/search). 2. Boundary markers: The output is formatted as JSON, providing a level of structural separation. 3. Capability inventory: The skill provides command execution capabilities via scripts/search. 4. Sanitization: The documentation does not describe specific sanitization or filtering of the API response before it is processed by the agent.
[SAFE]: No malicious patterns such as prompt injection, persistence mechanisms, or unauthorized data exfiltration were detected. The skill's behavior aligns with its stated purpose of providing a search interface for biochemical data.

chembl-search