Security audit
Security checks for vulnerabilities and agentic risk
This skill is a search/content-extraction guide, but it requests broad command and file authority while the package does not include the scripts it tells the agent to run.
Review carefully before installing. Only use this skill if you know which search.js and content.js scripts will run, trust their source, and are comfortable giving the agent command execution and local file-writing ability. Avoid using it for broad SEO automation unless you explicitly control the commands and saved outputs.
The activation criteria are broad and ambiguous, especially around SEO optimization, keyword analysis, ranking improvement, and traffic optimization. Overbroad triggers can cause the agent to invoke this skill in contexts beyond simple search/content retrieval, increasing the risk of misuse, unnecessary external queries, or execution of linked command workflows.
The security section claims command execution is limited to a whitelist and that sensitive data will not be exposed, but the manifest grants generic exec and write access without any visible enforcement mechanism. This creates a dangerous trust gap: agents or users may rely on safety guarantees that do not actually exist, enabling arbitrary command execution, file modification, or accidental disclosure.
The skill is presented as a Brave Search/content-extraction tool, but later claims broad automation, file processing, API integration, and command-execution capabilities that exceed the stated purpose. This kind of scope drift can mislead an agent into applying the skill in unrelated contexts and increases the chance of unnecessary file or command operations under a trusted search-tool label.
The documentation shows saving extracted content to a local file but does not clearly warn that this modifies the local filesystem. In an agent setting, even simple redirection can create unintended persistence of potentially sensitive remote content without explicit user awareness or consent.
The archiving example writes search results to disk with dated filenames but does not clearly disclose the persistence and retention implications. Search results and extracted page content may include proprietary, personal, or otherwise sensitive data, so silent archiving can create unnecessary local exposure.
No suspicious patterns detected.
