The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes shell commands using the GitHub CLI (gh) and git to automate repository creation and code deployment.
It hardcodes the --public flag in gh repo create, ensuring all new repositories are visible to the public by default.
[DATA_EXFILTRATION]: The execution of git add -A followed by a push to a public repository creates a high risk of accidental data leakage.
If the target directory contains sensitive information such as .env files, SSH keys, or hardcoded API tokens that are not explicitly ignored by the scaffolded .gitignore, these secrets will be published to GitHub.
[PROMPT_INJECTION]: The skill processes local project files to infer context and generate social media posts, creating a surface for indirect prompt injection (Category 8).
Ingestion points: Files located at the user-provided <path> or directory.
Boundary markers: None; the skill lacks explicit delimiters or warnings to the agent to ignore instructions embedded within the processed project files.
Capability inventory: Repository creation (gh repo create), file staging/pushing (git), and social media content generation.
Sanitization: No evidence of sanitization or filtering for the content read from project files before it is used to generate prompts for social posts or repository descriptions.

ship