darwin-core

Pass

Audited by Gen Agent Trust Hub on May 16, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The scripts/sync.py utility fetches Darwin Core term definitions and specifications from the Taxonomic Databases Working Group (TDWG) official GitHub repository. These are public, non-executable data standard files provided by a well-known organization in the biodiversity informatics community.
  • [PROMPT_INJECTION]: The skill parses and outputs content from untrusted user-provided files, such as Darwin Core Archives (ZIP/XML) and CSV datasets, which presents a surface for indirect prompt injection attacks.
  • Ingestion points: scripts/validate.py (reads filenames and meta.xml attributes) and scripts/map_columns.py (reads CSV column headers).
  • Boundary markers: None. The scripts print data retrieved from files directly to the console/agent context without using delimiters or protective warnings.
  • Capability inventory: The skill has the ability to create directories and write files to the local system via scripts/generate_template.py and scripts/map_columns.py.
  • Sanitization: No validation, escaping, or structural sanitization is performed on the strings read from external files before they are processed or displayed.
Audit Metadata
Risk Level
SAFE
Analyzed
May 16, 2026, 01:22 PM
Security Audit — agent-trust-hub — darwin-core