The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses shell commands to interact with the local environment and git repository.
Commands include git, awk, wc, and cat for data extraction and report generation.
The cat command is used to write the final review report to a local file in the current working directory.
[PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection (Category 8) because it processes untrusted input from code diffs.
Ingestion points: Git diff output is parsed in SKILL.md and passed to AI reviewers.
Boundary markers: No explicit delimiters or instructions are used in reviewers/gemini-role.md, reviewers/codex-role.md, or reviewers/claude-role.md to prevent the AI from obeying instructions embedded in the code being reviewed.
Capability inventory: The skill can execute shell commands and write files locally via SKILL.md.
Sanitization: There is no evidence of sanitization or filtering of the diff content before it is included in the prompts.

diff-review