game-wow-launch-circle

Pass

Audited by Gen Agent Trust Hub on May 12, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill performs shell-level operations using git (add, commit, push) and specified test_commands. It targets specific absolute file paths such as /Users/kjaylee/.openclaw/workspace/eastsea-blog for these operations.
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection through its data ingestion process.
  • Ingestion points: The agent reads from specs/game-idea-backlog.md, specs/daily-game-lv4.md, and specs/game-production-pipeline.md to determine game mechanics and implementation details.
  • Boundary markers: Absent. There are no instructions or delimiters provided to the agent to distinguish between data and potential instructions within these files.
  • Capability inventory: The skill possesses file-write capabilities (creating game files), sub-agent spawning, and network exfiltration via git push to a remote repository.
  • Sanitization: Absent. The skill does not include steps to sanitize or validate the content of the ingested markdown files before using them to drive the implementation phase.
Audit Metadata
Risk Level
SAFE
Analyzed
May 12, 2026, 08:03 AM