The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the Bash tool to execute gh issue view, git log, and git show to retrieve necessary information from the GitHub platform and local repository history.
[PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection by processing external data from GitHub issues.
Ingestion points: Untrusted content enters the agent's context through the output of the gh issue view command (SKILL.md).
Boundary markers: The instructions lack delimiters or explicit directives to treat the retrieved issue content as data only, potentially allowing embedded malicious instructions to influence the agent.
Capability inventory: The agent has access to the Bash tool for arbitrary command execution and the Write tool for file modification.
Sanitization: No input validation or filtering is performed on the data fetched from external issues before analysis.

create-checklist