alterlab-kegg

Pass

Audited by Gen Agent Trust Hub on Apr 12, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill communicates with the KEGG REST API (https://rest.kegg.jp) to retrieve bioinformatics data. This is a well-known and trusted scientific service.
  • [COMMAND_EXECUTION]: Network requests are implemented using the urllib standard library in scripts/kegg_api.py. The script uses a fixed base URL and provides URL-encoding for user-supplied search queries. No execution of arbitrary shell commands or untrusted scripts was found.
  • [DATA_EXFILTRATION]: No sensitive local data, such as credentials or environment variables, is accessed or transmitted. The skill's operations are strictly limited to information retrieval from a public scientific resource.
  • [SAFE]: Indirect Prompt Injection Surface Analysis: 1. Ingestion points: Genomic and pathway data from rest.kegg.jp via scripts/kegg_api.py. 2. Boundary markers: Absent in the raw text response handling. 3. Capability inventory: None. The skill does not possess file-write, subprocess execution, or dynamic code evaluation capabilities across any of its scripts. 4. Sanitization: Not performed on API responses, but the lack of exploitable capabilities and the trusted nature of the source mitigate the risk.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 12, 2026, 12:47 AM
Security Audit — agent-trust-hub — alterlab-kegg