The Agent Skills Directory

[SAFE]: The skill follows standard version control practices and does not contain code or instructions for data exfiltration, unauthorized access, or malicious persistence.
[PROMPT_INJECTION]: The skill is subject to indirect prompt injection risks as it instructs the agent to ingest and act upon untrusted external data (git diffs) and provides shell execution capabilities for commits and testing.
Ingestion points: Staged git diffs reviewed during the verification gate (SKILL.md).
Boundary markers: Absent; there are no instructions to use delimiters or ignore embedded instructions within the diff content.
Capability inventory: Shell command execution via git operations and project test suites (SKILL.md).
Sanitization: Absent; the skill does not require escaping or validation of content found within the diffs before processing.

commit