The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to use the dasel CLI tool for querying XML files and standard shell utilities like cat, diff, and redirection (>) for processing data.
Evidence: Examples such as cat chaosrouter_beans.xml | dasel -i xml '...' and diff /tmp/chaosrouter_beans.txt /tmp/integration_beans.txt demonstrate the use of system commands to perform bean discovery and dependency analysis.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external XML configuration files (e.g., applicationContext.xml), which could theoretically contain malicious instructions targeting the AI agent.
Ingestion points: The skill reads various Spring XML files (chaosrouter_beans.xml, integrationpoint_beans.xml, storage_beans.xml) via cat and dasel selectors.
Boundary markers: No specific boundary markers or instructions to ignore embedded commands are present in the provided patterns.
Capability inventory: The skill utilizes file system reading, command execution via dasel, and local file writing to /tmp/.
Sanitization: There is no evidence of sanitization or filtering of the content within the XML files before it is processed by the selectors.

enterprise-spring-xml