ClawAudit verdict
ai-daily
ai-daily-cn
The skill generates a daily AI news digest by scraping documented public sources (OpenAI, Anthropic blogs, arXiv, HuggingFace) using optional user-supplied Tavily/GitHub tokens — no suspicious data exfiltration or manipulation.
⚠ 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 (7)
Pipe to bash — executes piped content as shell commands
INSTALL.md · code · | bash
Possible hardcoded credential
INSTALL.md · code · API_KEY="tvly-xxxxxxxxxxxxxxxxxxxx
Pipe-to-shell pattern (curl | sh) — supply chain attack vector
INSTALL.md · code · curl https://pyenv.run | bash
Accesses shell history/config
README.md · code · ~/.zshrc
References sudo — requests elevated privileges
INSTALL.md · code · sudo
Python urllib.request — network access
config/prompts.md · code · urllib.request
Python os.environ.get — reads environment variable
config/prompts.md · code · os.environ.get(
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class A/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.
Is this flag fair?
Thanks — recorded.