The Agent Skills Directory

[CREDENTIALS_UNSAFE]: The SKILL.md file provides a shell command example containing a hardcoded password string YourStrongPassword123!. While intended as a placeholder, providing specific strings for sensitive credentials in documentation can lead to insecure configurations if adopted without modification.
[EXTERNAL_DOWNLOADS]: The file references/advanced-configuration.md contains a wget command directed at truststore.pki.rds.amazonaws.com to fetch the Amazon RDS CA certificate bundle. This is a standard requirement for verifying SSL/TLS connections to AWS RDS instances.
[COMMAND_EXECUTION]: The skill documentation describes using the Bash tool to execute network and database client commands, including telnet, curl, mysql, and psql, to verify connectivity and test application health endpoints.
[PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection as it is designed to read and manipulate local project files.
Ingestion points: The agent uses Read, Glob, and Grep tools to ingest content from local files such as pom.xml, application.properties, and SQL migration scripts.
Boundary markers: None identified; the instructions do not include specific delimiters or warnings to ignore instructions that might be embedded within the processed code or configuration files.
Capability inventory: The skill allows the use of the Bash tool for command execution and Write/Edit tools for modifying the local filesystem.
Sanitization: None identified; the skill does not specify procedures for validating or escaping content retrieved from the files before processing it.

aws-rds-spring-boot-integration