The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data which could contain malicious instructions designed to influence the agent's behavior.
Ingestion points: Data is ingested from git diff output, commit messages (git log), and various external files including coding standards (CODING_STANDARDS.md, CONTRIBUTING.md) and specification documents (paths under docs/, specs/, or .scratch/).
Boundary markers: There are no explicit instructions or delimiters used to warn the sub-agents to ignore instructions that might be embedded within the source code or specification text being reviewed.
Capability inventory: The skill utilizes shell command execution (git), sub-agent spawning via the Agent tool, and potential issue tracker integration as described in docs/agents/issue-tracker.md.
Sanitization: The skill does not implement any sanitization, filtering, or escaping of the ingested text before passing it to the sub-agents for analysis.

code-review