The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute various shell commands including git remote -v, gh issue commands, and glab issue commands. These are used to determine the repository's host and configure the environment by creating labels or reading existing issue data. These operations are consistent with the skill's purpose of repository setup.
[INDIRECT_PROMPT_INJECTION]: The skill establishes an attack surface for indirect prompt injection by directing the agent to ingest data from external sources.
Ingestion points: Issue bodies, comments, and pull request descriptions fetched from GitHub or GitLab via the gh and glab CLIs as described in issue-tracker-github.md and issue-tracker-gitlab.md.
Boundary markers: None are defined in the instructions; the agent is not provided with specific delimiters or instructions to ignore embedded commands within the fetched issue data.
Capability inventory: The skill allows the agent to write and modify files (e.g., CLAUDE.md, AGENTS.md, and files in docs/agents/) and perform authenticated writes to remote trackers (creating labels and commenting on issues).
Sanitization: There is no explicit sanitization or filtering of the content retrieved from issues or pull requests before the agent processes it.

setup-matt-pocock-skills