The Agent Skills Directory

[COMMAND_EXECUTION]: The skill requires the agent to execute a variety of shell commands using the GitHub CLI (gh), git, jq, and grep. These commands are used to verify project board status, manage branches, post review artifacts, and merge pull requests. These operations are core to the skill's stated purpose of automating issue-driven development.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources (GitHub issues and comments), which could potentially contain malicious instructions intended to influence the agent's behavior.
Ingestion points: Untrusted content is ingested from GitHub issue descriptions and comments via commands like gh issue view, gh issue lifecycle (referenced skill), and gh project item-list in SKILL.md.
Boundary markers: The skill does not define explicit delimiters or instructions for the agent to ignore or isolate instructions potentially embedded within the issue content it reads.
Capability inventory: The skill possesses significant capabilities that could be targeted by an injection attack, including file system access (writing and modifying code), shell command execution, and the ability to merge code into the repository.
Sanitization: There is no evidence of sanitization, filtering, or escaping applied to the content retrieved from GitHub before it is processed by the agent.
[DYNAMIC_EXECUTION]: The skill involves the dynamic creation and execution of code as part of its Test-Driven Development (TDD) workflow (Step 7). The agent is instructed to write implementation code and execute test suites, which is a standard and expected behavior for a coding assistant skill.

issue-driven-development