The Agent Skills Directory

[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted data from external GitHub issues.
Ingestion points: The gh issue view command retrieves external content from GitHub issues (SKILL.md).
Boundary markers: Absent. There are no delimiters or instructions to treat issue content as untrusted data.
Capability inventory: The skill has file system access (Read, Write, Edit) and can execute shell commands via gh and git (SKILL.md).
Sanitization: Absent. No sanitization or validation of the issue content is performed before the agent interprets it.
[COMMAND_EXECUTION]: The use of unquoted $issue in gh issue view $issue creates a command injection surface.
If the platform does not strictly validate the argument, shell metacharacters could be used to chain unauthorized commands despite the prefix restriction in allowed-tools.

fix-issue