The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external code, test files, Git history, and documentation (specifically docs/ARCHITECTURE.md). This untrusted data serves as a potential surface for indirect prompt injection attacks, where malicious instructions could be embedded within code comments or documentation to influence the agent's review process. The skill attempts to mitigate this through a structured, multi-stage protocol, but does not specify explicit sanitization for the ingested content.
[EXTERNAL_DOWNLOADS]: The skill documentation suggests installing a dependency using npx skills add jwilger/agent-skills --skill domain-modeling. This resource is associated with the skill's author (jwilger) and represents a standard extension of the skill's functionality via a vendor-controlled repository.

code-review