setup-game

Pass

Audited by Gen Agent Trust Hub on Aug 21, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill reads from potentially untrusted documentation files and interpolates that data into new project files and the project's AGENTS.md, which could allow instructions within the source files to influence the output.\n
  • Ingestion points: The skill reads docs/game/story.md, docs/game/puzzles.md, and docs/game/screenplay.md in step 1.\n
  • Boundary markers: No explicit boundary markers or instructions to ignore embedded commands are present when reading these files.\n
  • Capability inventory: The skill has the capability to write and modify multiple markdown files in the repository, including docs/game/world.md, docs/game/assets.md, docs/game/progress.md, and AGENTS.md.\n
  • Sanitization: There is no evidence of sanitization or filtering applied to the content read from the source documentation before it is written to the output files.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 21, 2026, 05:01 PM