The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the Bash tool to execute git diff and other system commands to collect context for code and plan reviews.
[PROMPT_INJECTION]: The skill is subject to potential indirect prompt injection as it reads and analyzes external, potentially untrusted content from the workspace.
Ingestion points: The skill ingests data via git diff output and by using the Read tool on Plans.md (as specified in SKILL.md).
Boundary markers: The skill lacks explicit delimiters or instructions for the agent to ignore embedded commands within the analyzed code or plan files.
Capability inventory: The skill possesses the Bash tool for command execution and the Task tool for modifying project state (as specified in SKILL.md).
Sanitization: There is no evidence of content sanitization or validation of the retrieved data before it is presented to the agent's context.

harness-review