The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests and processes untrusted external data from multiple sources which could contain malicious instructions targeting the agent context.
Ingestion points: The skill reads local files including DBMAP.md, source code files (*.rb, *.py, *.js, etc.), and application log files. It also accepts a user-provided SQL <query> for EXPLAIN analysis.
Boundary markers: The instructions lack explicit delimiters or "ignore embedded instructions" warnings when processing the content of logs or code files.
Capability inventory: The skill uses the Bash tool to execute psql, mysql, find, and grep commands, providing a functional path for any injected instructions to interact with the system environment.
Sanitization: There is no evidence of sanitization or validation of the user-provided SQL query before it is passed to the database execution tools.

db-optimize