The Agent Skills Directory

[SAFE]: The skill performs standard development tasks using established command-line tools including git and the GitHub CLI (gh).- [SAFE]: No obfuscation, unauthorized credential access, or data exfiltration to unknown domains was detected.- [INDIRECT_PROMPT_INJECTION]: The skill reads from local project files like design.md and plan.md to populate the PR body. This represents an ingestion point for untrusted data, but the use of the cat <<'EOF' pattern for shell interpolation follows safe practices for handling string content in shell scripts. The risk is considered inherent to the primary purpose of the skill.- [COMMAND_EXECUTION]: The skill executes shell commands for branch detection and diffing (git symbolic-ref, git diff). These operations are scoped to the local repository and are appropriate for the tool's functionality.

qrspi-pr