Serp Analysis

Security checks across malware telemetry and agentic risk

Overview

This is an instruction-only SERP research skill with expected web fetching and optional scoped memory saving; no code, credentials, install steps, or destructive behavior are shown.

This skill appears safe for SERP analysis if you are comfortable with the agent fetching public search-result pages and saving approved research summaries. Review linked external docs if the agent relies on them, and avoid granting broad SEO/Search Console access or saving sensitive strategy details unless needed.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Risk analysis

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.

#
ASI02: Tool Misuse and Exploitation
Info
What this means

The agent may make web requests and inspect third-party pages for the user’s query.

Why it was flagged

The skill is allowed to fetch live web/SERP pages, which is necessary for the stated analysis purpose and is disclosed.

Skill content
allowed-tools: WebFetch ... Always verify the live SERP
Recommendation

Use it for normal SERP research, and avoid providing private URLs or sensitive query context unless needed.

#
ASI03: Identity and Privilege Abuse
Info
What this means

If the user connects SEO tools or Search Console data, the agent could analyze private business or account information.

Why it was flagged

The skill mentions optional integrations that may involve account or tool data, but the artifacts do not require credentials or show token handling.

Skill content
Optional integrations: ~~SEO tool, ~~search console, ~~AI monitor.
Recommendation

Prefer read-only, narrowly scoped exports or screenshots unless live account access is clearly necessary.

#
ASI04: Agentic Supply Chain Vulnerabilities
Low
What this means

Some behavior may be shaped by linked documents outside the supplied artifact set.

Why it was flagged

The skill depends on linked external documentation that was not included in the reviewed file manifest, so those instructions were not fully reviewed here.

Skill content
Reads: goals, market inputs, tool data, and prior strategy from [CLAUDE.md](https://github.com/aaron-he-zhu/seo-geo-claude-skills/blob/main/CLAUDE.md) and the shared [State Model](https://github.com/aaron-he-zhu/seo-geo-claude-skills/blob/main/references/state-model.md) when available.
Recommendation

Review the linked documents before relying on them, or prefer bundled/local copies of referenced guidance.

#
ASI06: Memory and Context Poisoning
Low
What this means

Business strategy, keyword priorities, or competitor assumptions could persist and influence future tasks.

Why it was flagged

The skill can persist SERP conclusions and strategy notes into memory files that may be reused in later work.

Skill content
Promotes: durable keyword priorities, competitor facts, and pending strategy decisions to `memory/hot-cache.md`, `memory/open-loops.md`, and `memory/research/`.
Recommendation

Approve saved summaries intentionally and periodically review memory files for outdated, sensitive, or incorrect conclusions.