monetize-game

Pass

Audited by Gen Agent Trust Hub on Oct 23, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill integrates a remote JavaScript SDK into the game by adding a <script> tag pointing to https://sdk.play.fun/latest. This introduces a dependency on externally hosted code during the game's runtime.
  • [COMMAND_EXECUTION]: The instructions rely on executing several local scripts located in other skill paths, such as skills/playdotfun/scripts/playfun-auth.js and ~/.agents/skills/here-now/scripts/publish.sh. The security of this skill depends on the integrity of those referenced local components.
  • [INDIRECT_PROMPT_INJECTION]: The skill reads game metadata (name and description) from untrusted local files like package.json and interpolates this data into API requests and status messages.
  • Ingestion points: package.json, src/core/Constants.js, and $ARGUMENTS.
  • Boundary markers: None identified; metadata is used directly in JSON payloads.
  • Capability inventory: File system access, network requests (via curl and API calls), and deployment command execution.
  • Sanitization: No explicit sanitization or validation of the game metadata is performed before use.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 23, 2026, 12:31 PM