ClawAudit verdict
lunaclaw-brief
AI report generation skill that fetches data from public APIs (GitHub, arXiv, HackerNews, Yahoo Finance, etc.) and delivers via email/webhook; all data sources and delivery channels are documented and credentials are user-supplied.
⚠ 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.
Findings (5)
Possible hardcoded credential
SKILL.md · code · api_key: "your-key
Long base64 string (100+ chars) — likely obfuscated payload
static/luna_logo_b64.txt · prose · downgraded · iVBORw0KGgoAAAANSUhEUgAAAMgAAADICAIAAAAiOjnJAAAAAXNSR0IArs4c6QAAAERlWElmTU0AKgAA
Python os.getenv — reads environment variable
brief/llm.py · prose · downgraded · os.getenv(
Base64 encoding/decoding
brief/renderer/jinja2.py · prose · downgraded · base64-encode
Python aiohttp session — async network access
brief/sources/arxiv.py · prose · downgraded · aiohttp.ClientSession
Permissions & capabilities
No declared permissions — minimal attack surface.
credential_access Is this flag fair?
Thanks — recorded.