The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses shell commands for git, gh (GitHub CLI), and glab (GitLab CLI) to perform operations such as repository interaction, CI/CD job management, and merging pull requests.
[INDIRECT_PROMPT_INJECTION]: The skill has a vulnerability surface for indirect prompt injection due to its ingestion of external, user-controlled content from GitHub and GitLab.
Ingestion points: The skill fetches and processes pull request comments, reviews, and CI log traces via gh pr view, glab mr view, glab ci trace, and gh run view as described in the Procedure section of SKILL.md.
Boundary markers: Absent. There are no instructions or delimiters defined to separate the ingested external data from the skill's operational instructions.
Capability inventory: The skill is authorized to perform high-impact actions including git push, gh pr merge, glab mr merge, and glab ci retry.
Sanitization: Absent. The instructions do not specify any filtering, escaping, or validation of the content retrieved from external review comments or build logs.

shepherd