The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes git diff commands to retrieve file names and content changes from the current branch. This is the intended functionality for a PR readiness tool and does not involve arbitrary command execution or shell injection risks as the commands are static.
[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data in the form of branch diffs, which could contain malicious instructions embedded in code comments or strings intended to influence the agent's analysis.
Ingestion points: The git diff output is processed by the agent as instructed in repos/metamask-mobile.md to identify guideline violations.
Boundary markers: None identified; the skill processes the diff content directly.
Capability inventory: The skill has no capabilities to write files, access the network, or execute arbitrary subprocesses beyond the predefined git commands.
Sanitization: No explicit sanitization or filtering of the diff content is performed before analysis.

pr-readiness-check