ClawAudit verdict
daily-roleplay-game
This is an adult roleplay game engine with explicit kink/NSFW content generation, but all behavior is consensual, locally-contained, and user-directed — no exfiltration, no credential access, no remote code execution beyond documented image generation APIs.
⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
Automated static analysis — not a human review. ClawAudit flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
Permission integrity
agent_memory
Findings (5)
Possible hardcoded credential
docs/OPENCLAW_SETUP.md · code · token: "DISCORD_BOT_TOKEN
Pipe to python — executes piped content as Python code
engine/ENGINE.md · prose · downgraded · | Python
References agent memory files
SKILL.md · code · MEMORY.md
Instructs covert action — may act without user awareness
data/professions/business.yaml · prose · downgraded · quietly
Accesses OpenClaw config/secrets directly
docs/OPENCLAW_SETUP.md · prose · downgraded · ~/.openclaw/openclaw.json
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class B). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.
Permissions & capabilities
No declared permissions — minimal attack surface.
agent_memory Is this flag fair?
Thanks — recorded.