The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the gh and git command-line tools to interact with the repository and GitHub API. Specific actions include:
Checking authentication status via gh auth status.
Creating and pushing git branches (e.g., git push origin ...).
Managing GitHub labels, issues, and comments via gh issue and gh label subcommands.
[DATA_EXFILTRATION]: The skill transmits the contents of local specification files (context.md, .feature files) to GitHub by creating issues and comments. GitHub is a well-known and trusted service for development workflows.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes untrusted data from local specification files without explicitly defined sanitization or boundary markers.
Ingestion points: Reads contents from specs/<us-slug>/context.md, specs/<us-slug>/*.feature, and specs/<us-slug>/review.md.
Boundary markers: None identified; external content is interpolated directly into issue bodies.
Capability inventory: Full capability to create GitHub issues, post comments, and manage repository branches via gh and git CLI tools.
Sanitization: No explicit sanitization or filtering of the ingested markdown or Gherkin content is performed before processing.

to-issues-atdd