The Agent Skills Directory

[PROMPT_INJECTION]: Vulnerable to indirect prompt injection. * Ingestion points: Data is ingested from databases via scripts/query.sh and from CSV/Excel files via scripts/analyze_template.py. * Boundary markers: Absent. The skill does not implement delimiters or instructions to help the agent distinguish between data and commands. * Capability inventory: The skill allows for SQL execution and local file writing. * Sanitization: Absent. No validation or filtering is performed on external data before it enters the agent's context.
[COMMAND_EXECUTION]: Shell hygiene issue in scripts/query.sh. The mysql execution path uses an unquoted $DB_CONNECTION variable. This could result in argument injection or shell expansion if a connection string containing spaces or metacharacters is used.

data-analyst