The Agent Skills Directory

[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by ingesting and processing untrusted data from Git diffs and GitHub issues.
Ingestion points: Step 1 and Step 2 in SKILL.md gather data from git diff and external GitHub issue descriptions via $ARGUMENTS.
Boundary markers: Absent. The skill does not employ delimiters or specific instructions to isolate analyzed code or issue text from the agent's core instructions.
Capability inventory: The skill utilizes Bash for git and gh commands, along with Read and Grep tools, granting it broad access to repository contents.
Sanitization: No sanitization, escaping, or validation is performed on the content retrieved from Git or GitHub before it is processed by the agent.

review-branch