The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted code changes, creating a surface where malicious instructions in the code could attempt to influence the agent.
Ingestion points: The agent is instructed to read source code files and directory structures to find callers and dependencies.
Boundary markers: There are no specific instructions provided to the agent to use delimiters or to disregard embedded instructions within the code it reviews.
Capability inventory: The skill utilizes grep commands to perform recursive file searches and dependency tracing.
Sanitization: The instructions do not include steps to sanitize or validate the content of the files being analyzed for scope determination.

review-scope