The Agent Skills Directory

[PROMPT_INJECTION] (LOW): The skill's primary function is to ingest and analyze external source code, creating an attack surface for indirect prompt injection if the scanned files contain malicious instructions.
Ingestion points: The XSSScanner class uses fs.readFile in the scanDirectory method to read content from user-provided paths.
Boundary markers: Absent; there are no instructions to the agent to treat file content as data only or to ignore embedded instructions.
Capability inventory: The skill uses file system read access to analyze files.
Sanitization: No sanitization or escaping is performed on the ingested code before analysis.
[COMMAND_EXECUTION] (SAFE): The instructions suggest using standard security tools such as eslint-plugin-security and semgrep. These are recommended for development-time security auditing and do not represent malicious execution.
[DATA_EXPOSURE] (SAFE): The skill uses fs.readFile to access local source code files. This access is strictly aligned with the stated purpose of a security scanner, and no patterns indicating the exfiltration of this data to external domains were identified.

frontend-mobile-security-xss-scan