The Agent Skills Directory

[PROMPT_INJECTION]: The skill's primary function involves reading and analyzing untrusted code files or pull requests, which provides a vector for indirect prompt injection.
Ingestion points: Target code specified in the arguments is ingested using the Read tool across all review phases.
Boundary markers: The prompt instructions do not include boundary markers or explicit commands for the agent to ignore instructions embedded within the code being analyzed.
Capability inventory: The skill is authorized to use Read and Grep tools, permitting file system access for inspection but no network or write capabilities.
Sanitization: No sanitization, escaping, or validation is performed on the content of the files read from the target source.

design-review