The Agent Skills Directory

[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted data from pull requests.
Ingestion points: File contents and git diffs are read from the repository during the review workflow.
Boundary markers: The skill does not define delimiters or provide specific instructions to the agent to ignore embedded commands within the code being reviewed.
Capability inventory: The agent utilizes the Edit tool for filesystem modifications and Bash for git operations.
Sanitization: There is no process for sanitizing or validating the input data before processing.

pr-review