Security audit
Security checks for vulnerabilities and agentic risk
This skill appears to be a straightforward Google Trends lookup tool, with the main caution being mutable npx-based install instructions.
Install from a trusted, pinned source when possible, or use the manual copy path after reviewing the files. Expect the skill to make HTTPS requests to Google Trends with your search terms and selected region, date range, and locale. I found no evidence of persistence, credential access, local data harvesting, destructive actions, or hidden agent-control behavior in the audited artifact.
README.md:8Unpinned Third-Party Package Execution During Installation
Referenced artifact was not completely inspected
node scripts/trends.mjs <command> [options]
Referenced artifact was not completely inspected
node scripts/trends.mjs <command> [options]
Referenced artifact was not completely inspected
node scripts/trends.mjs <command> [options]
Referenced artifact was not completely inspected
node scripts/trends.mjs <command> [options]
Referenced artifact was not completely inspected
node scripts/trends.mjs <command> [options]
Referenced artifact was not completely inspected
node scripts/trends.mjs <command> [options]
Referenced artifact was not completely inspected
node scripts/trends.mjs <command> [options]
Referenced artifact was not completely inspected
node scripts/trends.mjs <command> [options]
The README instructs users to execute npx skills add terryds/google-trends-skill without pinning a specific package version. This allows whatever version is current at install time to run arbitrary package install logic, creating a supply-chain risk if the package is updated maliciously or compromised.
The command npx clawhub@latest install google-trends explicitly requests the latest version, which is mutable and may change over time. This increases exposure to supply-chain compromise because users will execute unreviewed code fetched at install time.
Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
npx clawhub@latest install google-trends
**Manual:** Copy this repo into your agent's skills directory (e.g. `.claude/skills/` or `.agents/skills/`).
## Commands
The skill instructs the agent to run a bundled Node.js script that fetches Google Trends data over the network, but the manifest declares no explicit tool scope such as network permissions or allowed-tools. Missing capability declarations weaken policy enforcement and review because downstream systems or operators cannot clearly tell that external network access is required. In an agent environment, this can enable unintended outbound requests or make it easier to smuggle network behavior into a seemingly simple skill.
The README describes fetching Google Trends data but does not clearly warn that the skill sends outbound requests to Google services. In an agent-skill context, undisclosed network access can surprise operators, affect privacy expectations, and violate restricted-runtime assumptions.
The reference specifies en-US as the default language for results, which is a natural-language locale choice presented as the default behavior. Because the document does not explain why English is required or note any user choice around locale, this may conflict with language/locale policy expectations.
Multiple functions hard-code English locale defaults such as hl = 'en-US' and lang = 'en', which causes the skill to operate in a specific language unless the caller overrides it. This is a natural-language policy concern because the file imposes an English locale by default rather than offering a neutral default or explicit user opt-in.
No suspicious patterns detected.