The Agent Skills Directory

[DATA_EXFILTRATION]: The skill utilizes the gh CLI to create issues on GitHub, transmitting data derived from the codebase to an external service. This is a core function of the skill and targets a well-known service.
[COMMAND_EXECUTION]: The skill runs local commands using the gh tool and an exploration agent to analyze the repository and manage issues. These actions are consistent with the skill's stated purpose of triaging bugs.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection by processing untrusted content from the codebase being triaged. Malicious instructions embedded in the code could potentially influence the agent's analysis or the resulting GitHub issue.
Ingestion points: The Agent tool with subagent_type=Explore reads source files, dependencies, and git logs from the repository.
Boundary markers: No specific delimiters or instructions are provided to the sub-agent to distinguish between codebase content and operational instructions.
Capability inventory: The skill uses an exploration agent to read the filesystem and the gh CLI to create issues.
Sanitization: The skill does not specify any sanitization or validation of the content extracted from the codebase before it is used to generate the issue.

triage-issue