The Agent Skills Directory

[SAFE]: The skill follows security best practices by explicitly prohibiting destructive git commands such as git reset --hard, git clean -fd, and force pushing in its safety section.
[SAFE]: The workflow is confined to standard, non-destructive git operations for synchronizing with an upstream repository, requiring user interaction for conflict resolution.
[PROMPT_INJECTION]: A potential surface for indirect prompt injection exists because the skill processes external data from the local repository state.
Ingestion points: The skill reads and evaluates output from git status and git remote -v to determine the synchronization path (SKILL.md).
Boundary markers: There are no explicit markers or instructions to ignore potential commands embedded in repository metadata.
Capability inventory: The skill has the authority to execute git fetch and git merge based on the ingested data (SKILL.md).
Sanitization: No specific validation or sanitization of branch names or remote URLs is described prior to command execution.

aiagent-material-sync