The Agent Skills Directory

[PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection by processing external data to generate release artifacts.
Ingestion points: Extracts information from git log commit messages, package.json version data, and existing changelog files within SKILL.md.
Boundary markers: The instructions do not provide explicit delimiters or instructions for the agent to ignore or isolate data found within the ingested git logs and files.
Capability inventory: The skill has the capability to execute shell commands (git), modify repository files (version file, changelog), and create pull requests.
Sanitization: No sanitization or filtering mechanisms are specified for the data summarized into release notes and changelog entries.
[COMMAND_EXECUTION]: The skill uses local shell commands to perform repository operations.
Evidence: Executes git fetch, git ls-remote, git log, and git show in the verification steps of SKILL.md. These commands are standard for release management and are used according to the skill's primary purpose.

cut-release