skills/openai/plugins/chembl-skill/Gen Agent Trust Hub

chembl-skill

Pass

Audited by Gen Agent Trust Hub on Sep 20, 2026

Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • Flexible Network Access: The skill utilizes a generic REST client that can communicate with external services. While it defaults to the ChEMBL API, the script allows for the base_url and path to be controlled via input, which could be used to interact with other network resources.
  • File System Write Access: The save_raw and raw_output_path parameters allow the skill to write API responses to the local file system. This is intended for saving data but could theoretically be used to write files to arbitrary locations if not carefully constrained.
  • Indirect Prompt Injection Surface: The skill processes external data from the ChEMBL API and returns summaries to the agent context. This creates a surface where instructions embedded in biological or chemical data (e.g., in text-search results) could potentially influence the agent's behavior, although the risk is low due to the structured nature of the data.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 20, 2026, 12:20 PM
Security Audit — agent-trust-hub — chembl-skill