The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze external code, diffs, and developer instructions, creating a potential surface for indirect prompt injection where malicious instructions could be embedded in the reviewed data.
Ingestion points: The skill reads proposed changes, instructions, and test results from the project files.
Boundary markers: No explicit delimiters or instructions to ignore embedded commands within the processed data are present in the skill definition.
Capability inventory: The skill is configured to use the Bash tool for command execution and Read, Glob, and Grep for file system access.
Sanitization: There is no mention of sanitization or validation for the data being processed.

vibe-review