The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes git and gh (GitHub CLI) commands to retrieve history, tags, and pull request data. These are standard operations for generating development documentation.
[PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it processes untrusted data from git commits and pull request metadata which could contain malicious instructions.
Ingestion points: Processes commit messages via git log and pull request details (titles, labels, bodies) via gh pr list as defined in SKILL.md.
Boundary markers: Absent. The skill does not define explicit delimiters or instructions to ignore embedded commands within the processed commit or PR data.
Capability inventory: Executes subprocesses for git and gh, and performs file-write operations to CHANGELOG.md as described in SKILL.md.
Sanitization: Absent. There is no mention of escaping or validating the content retrieved from the git history or GitHub API before inclusion in the final document.

doc-changelog