Ai Daily

AdvisoryAudited by Static analysis on Apr 30, 2026.

Overview

No suspicious patterns detected.

Findings (0)

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

ConcernHigh Confidence

ASI07: Insecure Inter-Agent Communication

What this means

If invoked, the skill could post the generated report and local report path to an unintended DingTalk group using the user's OpenClaw messaging authority.

Why it was flagged

This script sends the report summary through OpenClaw to a specific hard-coded DingTalk group/session rather than a user-configured destination.

Skill content

SUMMARY=$(head -60 "$REPORT_FILE") ... openclaw sessions send --session "agent:main:dingtalk:group:cid+sxosobsr081ckhs0jpsqw==" --message "$MESSAGE"

Recommendation

Remove the hard-coded session ID, require the user to configure the destination, and ask for confirmation before sending to any external chat.

ConcernHigh Confidence

ASI02: Tool Misuse and Exploitation

What this means

A network attacker or proxy could tamper with fetched articles, links, or summaries that appear in the generated report.

Why it was flagged

The fetcher disables TLS hostname and certificate verification for network requests, reducing integrity protection for HTTPS feeds and APIs.

Skill content

self.ssl_context.check_hostname = False
        self.ssl_context.verify_mode = ssl.CERT_NONE

Recommendation

Use the default verified SSL context; if a specific source needs an exception, make it explicit, narrow, and user-configurable.

NoteHigh Confidence

ASI02: Tool Misuse and Exploitation

What this means

This may violate source-site expectations or cause blocking; it is not hidden, but users should understand the scraping behavior.

Why it was flagged

The configuration explicitly notes using a real browser User-Agent to bypass Cloudflare for one source.

Skill content

"note": "使用真实浏览器 UA 绕过 Cloudflare"

Recommendation

Prefer official RSS/API sources or clearly document any scraping workaround and let users disable it per source.

NoteHigh Confidence

ASI10: Rogue Agents

What this means

If enabled, the skill will continue making network requests and writing reports on a schedule until the user removes the job.

Why it was flagged

The documentation shows how to create a recurring daily job for the skill.

Skill content

0 8 * * * cd /home/admin/.openclaw/workspace/skills/ai-daily && bash scripts/generate.sh >> /var/log/ai-daily.log 2>&1

Recommendation

Enable scheduled execution only if desired, review the exact command and output path, and keep removal instructions handy.

NoteHigh Confidence

ASI03: Identity and Privilege Abuse

What this means

These keys can grant access to external provider quotas or account features if configured.

Why it was flagged

The setup guide recommends optional provider credentials for search, LLM processing, and rate-limit improvements.

Skill content

export TAVILY_API_KEY="tvly-xxxxxxxxxxxxxxxxxxxx"
export ALIBABA_CLOUD_API_KEY="sk-xxxxxxxxxxxxxxxxxxxx"
export GITHUB_TOKEN="ghp_xxxxxxxxxxxxxxxxxxxx"

Recommendation

Use only the optional keys you need, scope them minimally, and avoid storing broad or personal tokens in shared shell profiles.