The Agent Skills Directory

[SAFE]: The skill uses the official GitHub CLI (gh) to interact with GitHub, which is a well-known and trusted service. No external downloads from untrusted sources are performed.
[COMMAND_EXECUTION]: The skill facilitates the execution of gh issue create commands. The provided examples use single-quoted heredocs (cat <<'EOF'), which is a security best practice to prevent the shell from interpreting or executing any content within the issue body, such as command substitution or variable expansion.
[DATA_EXFILTRATION]: Network activity is limited to communications with GitHub via the official CLI tool for the intended purpose of issue creation. No evidence of unauthorized data collection or transmission to unknown third-party domains was found.
[INDIRECT_PROMPT_INJECTION]: The skill processes external data such as logs and investigation results to populate issue reports. This presents a surface for indirect prompt injection; however, the skill employs structured Markdown templates to create logical boundaries for the untrusted data, and the risk is considered low and inherent to the skill's primary function.

create-github-issue