The Agent Skills Directory

[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes untrusted data from source files and documentation.
Ingestion points: Reads content from docs/task/{ID}-{task-name}.md, docs/testing/{ID}-{task-name}.md, and various source code files identified by git.
Boundary markers: The skill does not define specific delimiters or instructions for the agent to ignore potentially malicious instructions embedded within the files being reviewed.
Capability inventory: The skill executes git diff and writes updated status/notes back to the task documentation files.
Sanitization: There is no evidence of content sanitization or validation to prevent instructions within code comments or documentation from influencing the agent's behavior.
[COMMAND_EXECUTION]: The skill uses git diff --name-only main...HEAD to programmatically identify changed files. This is a standard and safe use of version control tools for a quality gate skill.

simplify