The Agent Skills Directory

[COMMAND_EXECUTION] (LOW): The skill executes git diff main...HEAD to retrieve code changes from the current branch. This is a standard and expected operation given the skill's purpose of quizzing users on code diffs.
[PROMPT_INJECTION] (LOW): The skill is vulnerable to Indirect Prompt Injection (Category 8) because it processes untrusted source code without sanitization. Evidence Chain: 1. Ingestion points: The agent reads the output of git diff and the contents of every changed file (as specified in SKILL.md Step 2). 2. Boundary markers: Absent; there are no instructions to use delimiters or ignore instructions embedded within the code diffs. 3. Capability inventory: The skill can execute git commands and interact with the user via AskUserQuestion. 4. Sanitization: Absent; the skill does not mention filtering or escaping strings from the source code that might contain malicious instructions for the AI.

branch-quiz