game-opportunity-decision

Pass

Audited by Gen Agent Trust Hub on Aug 26, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill initiates the execution of a local script at game-opportunity/scripts/game-opportunity.mjs using Node.js to perform market analysis.- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection attack surface by processing untrusted data from external market research.
  • Ingestion points: The workflow ingests external data including keyword search volumes, market demand metrics, and game metadata during the daily decision process (Checklist items D01, D04, and D06).
  • Boundary markers: The instructions lack explicit delimiters or guidance to the agent to disregard instructions potentially embedded within the ingested market data or results.
  • Capability inventory: The skill has access to shell command execution (via node) and local file system write operations within the .rankup/ directory.
  • Sanitization: There is no evidence of sanitization, validation, or filtering of the external search volume and keyword data before it is processed.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 26, 2026, 08:31 AM
Security Audit — agent-trust-hub — game-opportunity-decision