The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external sources that could contain malicious instructions designed to influence the agent's behavior.\n
Ingestion points: Step 2 in SKILL.md uses gh pr view and gh pr diff to fetch Pull Request metadata, diff content, and existing comments into the agent's context.\n
Boundary markers: The skill lacks delimiters or explicit instructions to the agent to disregard embedded commands or formatting within the fetched data.\n
Capability inventory: The skill has the ability to execute shell commands and modify remote repository state via gh pr comment (Step 5).\n
Sanitization: There is no evidence of sanitization or filtering applied to the fetched content before it is processed by the LLM.\n- [COMMAND_EXECUTION]: The skill relies on the gh (GitHub CLI) for its core operations.\n
It executes commands including gh auth status, gh pr view, gh pr diff, and gh pr comment.\n
The use of a heredoc (EOF) in Step 5 to pass the explanation to gh pr comment is a safety best practice to prevent shell injection via the generated summary text.\n
User confirmation is required before the final write operation, serving as a manual checkpoint.

explain-this-pr