The Agent Skills Directory

[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface due to its core function of processing external code.
Ingestion points: The agent reads project files and git history to provide reviews (SKILL.md).
Boundary markers: The instructions lack delimiters or explicit warnings to ignore potential instructions embedded within the analyzed code.
Capability inventory: The agent has access to bash, git, and file system operations for its tasks (SKILL.md).
Sanitization: There is no evidence of input validation or content filtering for the code being reviewed.
[COMMAND_EXECUTION]: The skill explicitly authorizes the use of system-level command line tools.
Evidence: The 'Herramientas disponibles' section lists bash for executing commands and running tests, and git for reviewing history and creating commits (SKILL.md).

code-reviewer