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

bgee-skill

Pass

Audited by Gen Agent Trust Hub on May 2, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSDATA_EXFILTRATIONCOMMAND_EXECUTION
Full Analysis
  • File System Access: The skill includes parameters for reading local files (query_path) and writing data to the filesystem (raw_output_path). This is used to facilitate the management of large SPARQL queries and the storage of machine-readable results.
  • Network Interaction: The script performs GET and POST requests to the Bgee SPARQL endpoint at https://www.bgee.org/sparql/, which is a recognized bioinformatics resource for gene expression data.
  • Data Ingestion Surface: The skill processes and summarizes data from an external API, which is a potential surface for indirect prompt injection considerations.
  • Ingestion points: Data is retrieved from the external Bgee endpoint within scripts/sparql_request.py.
  • Boundary markers: The skill does not currently use specific delimiters to separate the ingested data from the agent's internal instructions.
  • Capability inventory: The scripts/sparql_request.py script has the capability to perform network requests (requests) and access the filesystem (pathlib).
  • Sanitization: The skill focuses on compacting and summarizing JSON responses for display but does not apply specific sanitization to the remote content.
Audit Metadata
Risk Level
SAFE
Analyzed
May 2, 2026, 03:27 PM