The Agent Skills Directory

[COMMAND_EXECUTION]: The scripts/changelog_generator.py script executes the git command using subprocess.run to retrieve commit messages for changelog generation. This execution follows security best practices by passing arguments as a list and not using a shell, which mitigates standard command injection risks.
[INDIRECT_PROMPT_INJECTION]: The skill contains a vulnerability surface as it processes external, potentially untrusted data from git logs or piped input to generate text.
Ingestion points: The scripts/changelog_generator.py script reads commit subjects from git log output or sys.stdin.
Boundary markers: No delimiters or boundary markers are used when outputting the generated changelog.
Capability inventory: The skill's scripts are limited to text processing and standard output; they do not perform file-system writes (other than stdout), network operations, or dynamic code execution.
Sanitization: No sanitization is performed on the commit message content during the grouping or rendering process.

roadmap-communicator