The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external issue trackers (GitHub and GitLab), which represents a potential attack surface for adversarial instructions embedded in issue bodies.
Ingestion points: The skill reads issue content, comments, and pull request data using gh issue view and glab issue view (see issue-tracker-github.md and issue-tracker-gitlab.md).
Boundary markers: The SKILL.md logic explicitly requires the agent to "Present findings and ask" and "Confirm and edit" before any files are written to the repository, ensuring human oversight.
Capability inventory: The skill has the capability to write configuration and documentation files to the local file system (CLAUDE.md, AGENTS.md, and the docs/agents/ directory).
Sanitization: The skill relies on user review of generated drafts as the primary defense against processing malicious external content.
[COMMAND_EXECUTION]: The skill relies on standard command-line tools to interact with the environment and external services.
Evidence: Execution of git remote -v to identify repository origin and extensive use of gh (GitHub CLI) and glab (GitLab CLI) for issue management operations. These commands are necessary for the skill's stated purpose and use official, well-known binaries.

setup-matt-pocock-skills