The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute various git and development-related commands.
Evidence: In SKILL.md, the agent is directed to use git fetch, git switch, git pull, git branch -r, and git status. It also requires running typecheckers and test suites during the development process.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input from tickets or specifications while maintaining command execution capabilities.
Ingestion points: SKILL.md defines the primary input as the work described by the user in the "spec or set of tickets."
Boundary markers: Absent. There are no explicit instructions or delimiters used to prevent the agent from following instructions embedded within the ticket content.
Capability inventory: The agent has the ability to execute shell commands (git, npm/test tools) and write to local files (docs/agents/branching.md).
Sanitization: Absent. The skill does not describe any validation or sanitization of the ticket content before the agent acts upon it.

implement-copy