The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data from external sources during a code review workflow.
Ingestion points: The skill reads content from git diff, git log (commit messages), and documentation files located in docs/, specs/, or .scratch/ as defined in SKILL.md.
Boundary markers: There are no explicit boundary markers or instructions to the agent to treat the code content as non-instructional data, which may lead the agent to follow instructions hidden in code comments or commit logs.
Capability inventory: The skill utilizes local git commands and the ability to spawn parallel sub-agents to process content.
Sanitization: The instructions do not specify any sanitization, filtering, or escaping of the diff content or commit messages before they are passed to the Standards and Spec sub-agents.

code-review