The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data in the form of code diffs which are analyzed by subagents. Ingestion points: Reads code from git diff and git diff --staged (SKILL.md, Step 1). Boundary markers: The instructions do not define specific delimiters or 'ignore' instructions for the diff content passed to subagents. Capability inventory: The skill spawns multiple subagents using the Agent tool. Sanitization: No explicit sanitization or filtering of the code diff content is performed before processing.\n- [COMMAND_EXECUTION]: The skill executes local git commands to scope the code changes for review.\n
Evidence: Calls git diff and git diff --staged (SKILL.md, Step 1).

review-swarm