The Agent Skills Directory

Indirect Prompt Injection (LOW): The skill is designed to process external files and has access to high-privilege tools like Bash and Write. This creates a vulnerability surface where malicious instructions inside a data file could attempt to influence the agent.
Ingestion points: Uses the Read tool to access data files.
Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the prompt template.
Capability inventory: Includes Bash, Write, and Edit tools which could be abused if an injection succeeds.
Sanitization: No sanitization or validation logic is specified for the content of processed files.
Command Execution (SAFE): The skill requests the Bash tool in allowed-tools. While this is a high-risk capability, it is consistent with the stated purpose of performing file format conversions and data pipeline tasks.

file-format-converter