The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute a shell command 'python3 {REPO_DIR}/shared/docx-generator.py' using arguments that include user-provided variables like '{근로자명}'. There is no mention of sanitizing these inputs, which makes the system vulnerable to command injection if a user provides a name containing shell metacharacters.
[PROMPT_INJECTION]: The skill allows users to provide existing contracts for analysis and review, creating a surface for indirect prompt injection. 1. Ingestion points: User-provided contract text or files in the initial review step. 2. Boundary markers: Absent; the skill does not use delimiters or instructions to ignore embedded commands within the input text. 3. Capability inventory: The skill has the ability to execute shell commands (Python script conversion) and write files to the local file system. 4. Sanitization: None identified; the skill directly processes and extracts data from the user input without validation.

employment-contract