skills/wu-yc/labclaw/drugbank-search/Gen Agent Trust Hub

drugbank-search

Pass

Audited by Gen Agent Trust Hub on Mar 13, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local bash and Node.js scripts (scripts/search, scripts/search.mjs) to interact with the search API and handle configuration settings. It uses a dynamic path resolution command to locate these scripts within the plugin environment.- [EXTERNAL_DOWNLOADS]: The skill connects to the Valyu API at api.valyu.ai to retrieve pharmacological data, drug mechanisms, and interaction information.- [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it processes and renders natural language content (such as drug descriptions and mechanisms) retrieved from the external DrugBank database.
  • Ingestion points: Drug information, mechanisms of action, and interaction data returned from the Valyu API search results.
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the skill's processing logic.
  • Capability inventory: The skill can execute shell commands via the included scripts/search utility.
  • Sanitization: The documentation does not specify any sanitization or filtering of the content returned by the API before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 13, 2026, 03:47 AM