google-maps-search-api-skill
This skill is designed to help users automatically extract business data from Google Maps search results. The Agent should proactively apply this skill when the user makes the following requests searching for coffee shops in a specific city, finding dentists or medical clinics nearby, tracking competitors' locations in a certain area, extracting business leads from Google Maps lists, gathering restaurant data for market research, finding hotels or accommodation options in a region, locating specific services like coworking spaces or gyms, monitoring new business openings in a neighborhood, collecting contact information and addresses for sales prospecting, analyzing price ranges and cuisines of local eateries, getting ratings and review counts for a list of businesses, exporting local business data into a CRM or database.
66
80%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
High
Do not use without reviewing
Security
1 high severity finding. You should review these findings carefully before considering using this skill.
W007: Insecure credential handling detected in skill instructions.
What this means
The skill handles credentials insecurely by requiring the agent to include secret values verbatim in its generated output. This exposes credentials in the agent’s context and conversation history, creating a risk of data exfiltration.
Why it was flagged
The skill tells the agent to check BROWSERACT_API_KEY and "ask and wait for the user to provide it" (and later to have the user "provide the correct API Key"), which effectively requires the LLM to solicit and may cause it to receive or handle the API key in chat, creating an exfiltration risk.
Low
Low-risk findings.
2 low severity findings. Worth noting, but not necessarily harmful.
W011: Third-party content exposure detected (indirect prompt injection risk).
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
The required workflow calls a public/third-party BrowserAct HTTP API at runtime, fetches the task’s `output.string` (populated from Google Maps/search results, including free-form review snippets), and prints/returns that text to the agent, which then feeds it into the LLM context for further use—an outsider-authored free-text injection path.
W012: Unverifiable external dependency detected (runtime URL that controls agent).
What this means
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
Why it was flagged
The script directly calls the BrowserAct API at runtime (https://api.browseract.com/v2/workflow) to start and poll a workflow template, causing remote execution of the BrowserAct workflow which the skill depends on.
- Repository
- browser-act/skills
- Commit
11c057b
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.