graphify-knowledge-graph

Pass

Audited by Gen Agent Trust Hub on Aug 1, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local Python harness script at .codex/skills/scripts/graphify_harness.py using user-provided parameters like project_dir and target to perform graph operations.- [INDIRECT_PROMPT_INJECTION]: The skill ingests content from external sources such as Obsidian vaults and codebase ASTs, creating a surface for potential instruction injection in processed data.
  • Ingestion points: Project directories and files processed by the indexing action.
  • Boundary markers: No specific delimiters or safety instructions are defined to separate data from instructions.
  • Capability inventory: The harness performs local file reads, writes to the .graphify/ folder, and CLI execution.
  • Sanitization: The skill description does not specify methods for sanitizing or validating the indexed content.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 1, 2026, 03:52 AM
Security Audit — agent-trust-hub — graphify-knowledge-graph