skills/kessriga/game-studio/adopt/Gen Agent Trust Hub

adopt

Pass

Audited by Gen Agent Trust Hub on Aug 24, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill performs local file auditing using a restricted toolset (Read, Glob, Grep, Write, AskUserQuestion) and does not perform network operations or access sensitive system credentials.
  • [SAFE]: The workflow requires explicit user confirmation before writing the adoption plan to the filesystem or executing suggested remediation steps.
  • [PROMPT_INJECTION]: The skill processes untrusted project files which provides a surface for indirect prompt injection. 1. Ingestion points: Markdown and YAML files in the design/, docs/, and production/ directories are read during Phase 1 and 2. 2. Boundary markers: No explicit delimiters or boundary markers are used when interpolating audited content into skill logic or generated reports. 3. Capability inventory: The skill is restricted to local filesystem interactions and user prompts, minimizing the impact of potential injection. 4. Sanitization: The audit process identifies specific structures but does not explicitly sanitize the full content of the audited files.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 24, 2026, 04:18 PM
Security Audit — agent-trust-hub — adopt