The Agent Skills Directory

[PROMPT_INJECTION]: The skill processes untrusted external data which introduces a risk of indirect prompt injection attacks.
Ingestion points: Data enters the agent context through git commit messages (via git log output) and local plan files like .version-update-plan.json.
Boundary markers: The instructions lack explicit boundary markers or delimiters to differentiate between static instructions and dynamic data being processed by the agent.
Capability inventory: The skill is configured to use the Bash and Read tools, providing the agent with the ability to execute shell commands and read filesystem content.
Sanitization: No explicit sanitization, validation, or escaping of the ingested commit messages or file content is performed prior to the agent generating the formatted changelog output.

generate-changelog