The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the repository environment to generate configuration files and engineering principles, creating a surface for indirect prompt injection.
Ingestion points: The skill reads git remote -v output, package.json scripts, and the names and content of documentation files in docs/prd/, docs/adr/, and docs/research/ (SKILL.md, REFERENCE.md).
Boundary markers: No explicit delimiters or warnings are used to isolate ingested data within the generated configuration templates.
Capability inventory: The skill can execute shell commands via git, gh, and glab CLIs, and perform file system operations including reading, writing, and renaming files (SKILL.md, REFERENCE.md).
Sanitization: There is no automated sanitization of ingested strings; however, the skill requires explicit user confirmation of the full draft before any files are written (SKILL.md Step 5).
[EXTERNAL_DOWNLOADS]: The skill includes a reference to the official GitLab CLI (glab) repository for documentation purposes (templates/issue-tracker-gitlab.md).
[COMMAND_EXECUTION]: The skill utilizes standard command-line tools including git, gh (GitHub CLI), and glab (GitLab CLI) to perform repository discovery and manage issue tracker configurations (SKILL.md, templates/issue-tracker-github.md).

setup-project