The Agent Skills Directory

[COMMAND_EXECUTION]: The skill provides shell scripts (scripts/analyze-schema.sh, scripts/index-advisor.sh, scripts/migration-plan.sh) designed to be executed by the agent to perform database maintenance and analysis. These scripts are local templates provided within the skill package.
[DATA_EXFILTRATION]: The provided helper scripts accept database credentials, including passwords, as command-line arguments. This method of credential handling poses a risk of data exposure as passwords may be captured in process lists, command history, or agent execution logs.
[PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection because it is designed to ingest and process data from external sources such as database schemas and slow query logs.
Ingestion points: Database metadata in scripts/analyze-schema.sh and log files in scripts/index-advisor.sh.
Boundary markers: No specific delimiters or boundary instructions are used to separate external data from agent instructions.
Capability inventory: The skill allows for command execution (shell scripts) and database interactions.
Sanitization: There is no evidence of sanitization or input validation performed on the data retrieved from external logs or database schemas within the provided script templates.

database-engineer