The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external sources that could potentially contain malicious instructions intended to influence the agent's behavior during PR generation.
Ingestion points: The skill fetches data from GitHub using gh issue list and the GitHub GraphQL API (gh api graphql) to analyze open issues and discussions.
Boundary markers: There are no explicit delimiters or instructions provided to the agent to treat the fetched GitHub content as untrusted data or to ignore embedded instructions.
Capability inventory: The skill possesses significant capabilities, including pushing code to remote repositories (git push), creating/updating Salesforce records (sf data create/update record), and modifying PR reviewers (gh pr edit).
Sanitization: The instructions do not specify any sanitization, filtering, or validation steps for the content retrieved from GitHub before it is processed by the LLM for relevance and inclusion in the PR.
[COMMAND_EXECUTION]: The skill utilizes several CLI tools to perform its tasks, which is standard behavior for development automation but involves executing shell commands based on branch names and environment data.
Evidence: Uses git push, git branch, git reflog, gh issue, gh api, and sf data commands to interact with the local environment and remote services.

pr-draft