The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses local shell commands to gather context about the repository and provides templates for interacting with remote issue trackers.
The skill executes git remote -v and reads .git/config to identify the project source.
Templates in issue-tracker-github.md and issue-tracker-gitlab.md provide a suite of commands using the gh and glab CLIs to create, list, and view issues and pull requests.
[INDIRECT_PROMPT_INJECTION]: The skill configures an attack surface for indirect prompt injection by instructing the agent to process data from external, user-controllable sources.
Ingestion points: Data from GitHub Issues, GitHub PRs, GitLab Issues, and GitLab Merge Requests are ingested via gh issue view and glab issue view as defined in the tracker templates.
Boundary markers: The generated configuration docs (docs/agents/issue-tracker.md) do not include specific delimiters or instructions for the agent to ignore potentially malicious instructions embedded in issue bodies or comments.
Capability inventory: The skill provides the agent with file-writing capabilities (to update CLAUDE.md, AGENTS.md, and create documentation) and CLI execution capabilities for repository management.
Sanitization: There is no evidence of sanitization, filtering, or validation of the content fetched from the remote issue trackers before it is processed by the agent.

setup-matt-pocock-skills