The Agent Skills Directory

Prompt Injection (SAFE): The skill contains well-defined instructions for its stated purpose of grammar checking and does not attempt to bypass safety filters or override agent constraints.- Data Exposure & Exfiltration (SAFE): No sensitive file paths, hardcoded credentials, or network-enabled tools were detected.- Obfuscation (SAFE): No encoded or hidden content, such as Base64 or zero-width characters, was found in any of the skill files.- Unverifiable Dependencies & Remote Code Execution (SAFE): The skill does not include any remote code downloads or external package installations.- Indirect Prompt Injection (LOW): The skill reads and processes untrusted text from users or files, which could contain embedded instructions. Although it is a standard utility, its access to tools like Write and Edit creates a theoretical risk of unauthorized file modification if the agent follows instructions found within the analyzed text. * Ingestion points: Ingests text directly from users or from local files via the Read tool. * Boundary markers: Instructions lack explicit delimiters or warnings to ignore instructions embedded in the target text. * Capability inventory: Metadata allows Read, Write, Edit, Grep, and Glob tools. * Sanitization: No input sanitization or validation logic is specified for the text being analyzed.

grammar-checker