graph-build

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a Python script (graph_build.py) located within the plugin's root directory to perform structural analysis on a codebase. It uses standard shell arguments to specify the target directory.
  • [INDIRECT_PROMPT_INJECTION]: This skill has an attack surface for indirect prompt injection because it ingests codebase content to build its knowledge graph.
  • Ingestion points: Reads files from the user-specified <dir> path as indicated in SKILL.md.
  • Boundary markers: None mentioned in the instructions to delimit untrusted file content.
  • Capability inventory: Executes a Python build script via shell command (python3).
  • Sanitization: No explicit sanitization or filtering of the ingested source code is described in the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 10:05 AM
Security Audit — agent-trust-hub — graph-build