The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill includes instructions to process external data sources such as project files, logs, and git history using tools like bash and git. This creates a surface for indirect prompt injection if those sources contain malicious instructions.
Ingestion points: The skill reads project files, git history, and system logs via bash and git tools (SKILL.md).
Boundary markers: There are no explicit instructions or delimiters defined to separate user-provided data from agent instructions or to ignore embedded commands.
Capability inventory: The agent is granted access to high-privilege tools including bash for command execution and file system operations for reading/writing project files (SKILL.md).
Sanitization: No validation or sanitization of the content retrieved from external files or command outputs is specified.

db-optimizer