The Agent Skills Directory

[COMMAND_EXECUTION]: The skill relies on shell commands for repository and issue management.\n
Evidence: The workflow in SKILL.md and rules/issue-and-branch-workflow.md utilizes git and gh commands.\n
Evidence: Command arguments such as issue titles, bodies, and branch names are constructed from user input and data fetched from GitHub.\n- [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface where malicious content in external GitHub issues could influence agent behavior.\n
Ingestion points: Issue data is fetched using gh issue view and gh issue develop --list as described in rules/issue-and-branch-workflow.md.\n
Boundary markers: There are no explicit instructions to the agent to treat external issue content as untrusted or to use delimiters to prevent instruction injection.\n
Capability inventory: The skill allows for shell command execution (git, gh) and file system interaction (branch management).\n
Sanitization: The instruction files do not specify validation or sanitization routines for the data retrieved from GitHub.

git-issue