pygraphistry-gfql

Pass

Audited by Gen Agent Trust Hub on Oct 4, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill facilitates processing graph data and user-provided queries. Ingestion points: User input strings through g.gfql() and gfql_remote() in SKILL.md. Boundary markers: Explicit instructions to 'Validate user-derived query fragments' and 'Preflight Cypher'. Capability inventory: Remote query execution via gfql_remote() and lambda execution via python_remote_table(). Sanitization: Recommends using parse_cypher and compile_cypher for validation.
  • [DYNAMIC_EXECUTION]: The skill uses python_remote_table, which allows for the remote execution of Python lambda functions on Graphistry servers, a feature central to the library's remote analytics engine.
  • [EXTERNAL_DOWNLOADS]: The skill references technical documentation on pygraphistry.readthedocs.io, which is a well-known service providing official project documentation.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 4, 2026, 04:37 PM