chembl-search

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION] (LOW): The skill executes local bash and Node.js scripts (scripts/search). It instructs the agent to use the find command to resolve script paths within the environment's plugin cache.\n- [EXTERNAL_DOWNLOADS] (LOW): The skill communicates with api.valyu.ai, which is not on the trusted domain whitelist. This behavior is documented and necessary for the skill's stated purpose.\n- [PROMPT_INJECTION] (LOW): The skill has a surface for indirect prompt injection by ingesting and processing search results from an external API.\n
  • Ingestion points: External chemical and assay data from api.valyu.ai via scripts/search.\n
  • Boundary markers: Absent. The documentation does not specify delimiters to separate untrusted data from the agent's instructions.\n
  • Capability inventory: Includes local script execution and network access.\n
  • Sanitization: No sanitization or escaping of the external API content is documented.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 05:33 PM