gds-generate-project-context

Pass

Audited by Gen Agent Trust Hub on Jul 7, 2026

Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a Python script located at {project-root}/_bmad/scripts/resolve_customization.py during both the activation and completion phases. It also provides an execution surface for arbitrary commands via the activation_steps_prepend, activation_steps_append, and on_complete configuration fields.
  • [DATA_EXFILTRATION]: The skill is designed to read and analyze various project files to gather technical context, including architecture documents, engine-specific configuration files (Unity, Unreal, Godot), and dependency manifests like package.json and requirements.txt.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it ingests data from external project files which could contain malicious instructions. 1. Ingestion points: steps/step-01-discover.md (reads architecture docs and manifests). 2. Boundary markers: No specific delimiters were found to isolate ingested content from instructions. 3. Capability inventory: Shell command execution via local Python scripts and file system write access. 4. Sanitization: No content validation or sanitization was observed for the ingested files.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 7, 2026, 06:21 PM
Security Audit — agent-trust-hub — gds-generate-project-context