The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes local git commands, including git log and git diff, to analyze repository history and code changes for release note generation.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its processing of potentially untrusted project data that may contain malicious instructions. 1. Ingestion points: Commit messages from git logs and source code content from repository files. 2. Boundary markers: Absent; the skill does not use delimiters to isolate ingested data from instructions. 3. Capability inventory: File system read/write access (updating CHANGELOG.md and modifying source code) and the ability to trigger the project-documentation skill. 4. Sanitization: No validation or filtering is applied to commit messages or code contents before they are processed by the agent.

release