The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted content from the local codebase, which introduces a potential surface for indirect prompt injection.
Ingestion points: The skill utilizes Grep and Read tools to analyze existing query patterns and database code within the repository to inform new code generation and auditing tasks (SKILL.md).
Boundary markers: The instructions do not specify the use of clear delimiters or boundary markers to isolate content read from the codebase from the agent's internal instructions.
Capability inventory: The agent is authorized to use Edit, Write, and Bash tools, which could be misused if the agent's logic is influenced by malicious content found in the codebase.
Sanitization: The skill focuses on promoting secure SQL practices in the output but lacks explicit instructions for the agent to sanitize or ignore instructions embedded within the data it reads from the repository.

golang-database