atlan-fact-verification-gate

Pass

Audited by Gen Agent Trust Hub on Feb 24, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local validation script using the command 'python ../_shared/scripts/validate_verification_manifest.py'. This script is part of the vendor's internal shared infrastructure for manifest integrity.
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it is designed to ingest and interpret external data from SDK source code and documentation.
  • Ingestion points: SDK code files, documentation pages, and local/remote source guides.
  • Boundary markers: No explicit boundary markers or delimiters are used to isolate content ingested from external sources.
  • Capability inventory: The skill performs file read/write operations and executes a local Python script.
  • Sanitization: No explicit sanitization or filtering of the content retrieved from SDK or CLI sources is defined before interpretation.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 24, 2026, 06:22 PM