ClawAudit verdict
AI前沿哨兵
ai-intelligence-sentinel
A web intelligence aggregation tool that uses web search and fetch tools to compile AI industry news reports saved to local markdown files; the content includes a self-declared security statement and all behaviors are consistent with the stated news aggregation purpose.
⚠ 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
references/api_setup.md · code · token: "YOUR_BEARER_TOKEN_HERE
Pipe to python — executes piped content as Python code
reports/2026-04-10/xiaohongshu_report.md · prose · downgraded · | Python
References agent memory files
SKILL.md · code · MEMORY.md
Python os.environ.get — reads environment variable
references/api_setup.md · code · os.environ.get(
Python urllib.request — network access
VIRUSTOTAL_FALSE_POSITIVE.md · code · urllib.request
Permissions & capabilities
No declared permissions — minimal attack surface.
agent_memory Is this flag fair?
Thanks — recorded.