The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses local shell commands including git and gh (GitHub CLI) to perform repository management operations such as branching, merging, tagging, and creating GitHub releases. These operations are within the standard scope of the skill's intended purpose.
[INDIRECT_PROMPT_INJECTION]: The skill has an inherent attack surface for indirect prompt injection because it reads and processes externally-sourced text (Pull Request titles and commit messages) to generate entries for CHANGELOG.md and release notes.
Ingestion points: PR subjects and squashed commit messages are used to build the changelog as described in references/changelog.md.
Boundary markers: No explicit delimiters or instructions are provided to the agent to prevent the interpretation of instructions that might be embedded within PR titles or commit messages.
Capability inventory: The agent has the capability to write to the local file system (CHANGELOG.md, project manifests), execute shell commands (git, gh), and perform network operations via the GitHub CLI.
Sanitization: There is no explicit sanitization or validation logic for the external text before it is interpolated into files or CLI command arguments.

gitflow