The Agent Skills Directory

[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface (Category 8) due to its core functionality of reading and analyzing external codebase data.
Ingestion points: In Phase 1 and Phase 2, the skill uses the Read and Grep tools to ingest content from the target codebase (as defined in references/hunter-prompt.md and references/skeptic-prompt.md).
Boundary markers: The skill interpolates report data and codebase content directly into subagent prompt templates (e.g., <HUNTER_REPORT>) without using specific delimiters or "ignore embedded instructions" warnings to separate data from the subagent's mission instructions.
Capability inventory: The subagents utilize feature-dev:code-reviewer and general-purpose types, possessing the ability to read files and traverse directories using Glob, Read, and Grep tools.
Sanitization: There is no evidence of sanitization, escaping, or validation of the codebase content before it is processed by the subagents.

bug-hunt