Back to skill
v1.0.2

Design Daily

BenignClawScan verdict for this skill. Analyzed May 1, 2026, 7:35 AM.

Analysis

Design Daily appears to do what it claims—fetch design news and summarize it with Serper and DeepSeek—but users should protect the API keys it stores locally and only enable the optional daily schedule intentionally.

GuidanceThis looks reasonable for a design-news briefing skill. Before installing, use separate low-limit API keys, keep the generated .env file private, run preview mode first, verify important news links, and only enable the cron example if you want daily API usage and local log/output files.

Findings (4)

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.

Abnormal behavior control

Checks for instructions or behavior that redirect the agent, misuse tools, execute unexpected code, cascade across systems, exploit user trust, or continue outside the intended task.

Agentic Supply Chain Vulnerabilities
SeverityInfoConfidenceHighStatusNote
requirements.txt
requests>=2.28.0
pyyaml>=6.0

The install uses common Python packages, but versions are not exactly pinned or hash-locked.

User impactFuture installs may resolve to newer package versions than the author tested.
RecommendationInstall in a virtual environment and consider pinning exact versions or using a lockfile for repeatable installs.
Agent Goal Hijack
SeverityLowConfidenceMediumStatusNote
brief.py
f"    摘要:{item.get('snippet', '')}",
            f"    链接:{item.get('url', '')}",

Search-result snippets and links are inserted into the model prompt for summarization; these are untrusted web-derived inputs.

User impactA bad or misleading search result could influence the generated brief or links, though the visible code does not give the model tool-execution authority.
RecommendationTreat generated briefs as summaries, verify important claims and links, and consider adding prompt instructions that explicitly treat search snippets as untrusted source material.
Rogue Agents
SeverityLowConfidenceHighStatusNote
SKILL.md
0 9 * * * cd /path/to/Design_Daily && python run.py >> logs/cron.log 2>&1

The documentation provides an optional cron entry that would run the skill automatically every day.

User impactIf enabled, the skill will continue making API calls and writing logs on a schedule until the user removes the cron job.
RecommendationOnly add the cron job if recurring execution is desired, monitor API usage and logs, and remove the schedule when no longer needed.
Permission boundary

Checks whether tool use, credentials, dependencies, identity, account access, or inter-agent boundaries are broader than the stated purpose.

Identity and Privilege Abuse
SeverityLowConfidenceHighStatusNote
setup.py
env_path.write_text(
        f"SERPER_API_KEY={serper_key}\n"
        f"DEEPSEEK_API_KEY={deepseek_key}\n",

The setup wizard stores user-provided provider API keys in a local .env file, and the runtime later uses those keys for Serper and DeepSeek calls.

User impactAnyone who can read the skill directory may be able to see keys that can spend the user's Serper or DeepSeek quota.
RecommendationUse dedicated low-limit API keys, keep the .env file private, avoid committing it to source control, and revoke/regenerate keys if exposed.