The Agent Skills Directory

[COMMAND_EXECUTION]: The script scripts/autocorrect.ts uses execSync to invoke a shell command that includes a file path variable (filePath). While the variable is enclosed in double quotes, this pattern can be susceptible to command injection if a malicious file name containing backticks or shell expansion characters is processed.
[EXTERNAL_DOWNLOADS]: The skill uses npx to dynamically download and execute the autocorrect-node package at runtime in scripts/autocorrect.ts, and the SKILL.md instructions similarly use npx -y bun to run the main script. This results in execution of code not pinned to specific versions.
[REMOTE_CODE_EXECUTION]: Use of npx within scripts and instructions facilitates the remote execution of packages fetched at runtime.
[PROMPT_INJECTION]: The skill processes untrusted user data in the form of arbitrary text or markdown files and has access to powerful capabilities like shell execution. Ingestion points: Markdown or plain text files provided by the user. Boundary markers: The skill lacks explicit prompt delimiters or instructions to ignore embedded commands within the processed files. Capability inventory: The skill can execute shell commands via execSync and write files to the disk. Sanitization: Content is handled via AST transformation, but the file path itself is not sanitized before being passed to a shell command.

baoyu-format-markdown