The Agent Skills Directory

[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it ingests untrusted source code changes from git diff and processes them to generate a review.
Ingestion points: The git diff command output from the local repository (SKILL.md).
Boundary markers: None; the skill does not use specific delimiters or instructions to ignore potential commands within the code diff.
Capability inventory: The skill has access to file system tools (Write, Edit) and shell execution (bash).
Sanitization: No sanitization or escaping of the code content is performed before analysis.
[COMMAND_EXECUTION]: The skill utilizes the system shell to perform repository inspections and file management tasks.
Executes git rev-parse, git diff, date, and basename to gather project information and generate file paths (SKILL.md).
[DATA_EXFILTRATION]: The skill extracts source code snippets through the review process and writes them to a separate Obsidian vault repository, which is subsequently pushed to a remote repository via the ai-commit skill.

ai-full-code-review