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

changelog

Pass

Audited by Gen Agent Trust Hub on Aug 24, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [DYNAMIC_CONTEXT_INJECTION]: The skill uses hardcoded git commands in the context field to fetch repository metadata during initialization.
  • [COMMAND_EXECUTION]: The skill uses the Bash tool to execute git commands for analyzing repository history.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data which could contain malicious instructions. 1. Ingestion points: commit messages via git log and files in backlog/tasks/ and design/gdd/. 2. Boundary markers: None present. 3. Capability inventory: Bash and Write tools. 4. Sanitization: No filtering or validation of external input.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 24, 2026, 04:18 PM
Security Audit — agent-trust-hub — changelog