The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the repository to perform reviews, creating a surface for indirect prompt injection.
Ingestion points: git diff output, git log output (commit messages), issue tracker files (docs/agents/issue-tracker.md), and specification documents (docs/, specs/, .scratch/).
Boundary markers: None identified. The instructions do not explicitly tell the sub-agents to ignore instructions found within the data being analyzed.
Capability inventory: The skill uses git for data retrieval and the Agent tool to spawn sub-agents to process the data.
Sanitization: No sanitization or validation of the ingested content is performed before passing it to the sub-agents.

review