The Agent Skills Directory

Command Injection Surface: The skill embeds user-provided variables like {{version}} and {{commit_sha}} directly into shell commands such as git rev-parse and git cherry-pick. This pattern represents a security consideration because characters intended for shell redirection or command chaining could be used to execute unintended operations in a terminal environment.
Indirect Prompt Injection Surface: The skill processes external inputs which could potentially be used to influence the agent's behavior during automated tasks.
Ingestion points: Commit identifiers and version strings provided via user input (SKILL.md)
Boundary markers: None detected
Capability inventory: Execution of shell commands via the git CLI (SKILL.md)
Sanitization: No explicit input validation or escaping logic is described in the skill instructions.

hotfix-release