The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external GitHub pull requests which represents a vulnerability surface for indirect prompt injection.
Ingestion points: The skill uses gh pr view and gh pr diff in SKILL.md to retrieve titles, bodies, and diffs from pull requests.
Boundary markers: No specific delimiters or "ignore embedded instructions" directives are defined to separate untrusted PR content from the agent's instructions.
Capability inventory: The skill can read local project files (README.md, CLAUDE.md), execute shell commands via the GitHub CLI (gh), and spawn additional subagents via the Agent tool.
Sanitization: The instructions do not include steps to sanitize, escape, or validate the content retrieved from GitHub before it is processed by the agent or passed to sub-agents.

review-pr