The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted external data from Linear issues and comments to establish implementation and design context for its review process.
Ingestion points: Linear issue descriptions, parent issues, and specifically comments tagged with ## Grilling outcome in SKILL.md.
Boundary markers: The skill does not define specific delimiters or instructions to ignore potential commands embedded within the external Linear data.
Capability inventory: The skill has the ability to read local source files (staged, unstaged, and untracked) and perform write operations to the Linear API (marking acceptance criteria as done).
Sanitization: No evidence of sanitization or validation of the ingested external content is present.

review-implementation