The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources, which could contain malicious instructions designed to influence the agent's behavior during ticket generation.
Ingestion points: External references, such as issue bodies, comments, and specification files fetched from user-provided URLs or identifiers (SKILL.md).
Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions when processing fetched external content.
Capability inventory: The skill utilizes the GitHub CLI (gh) to create issues and writes to the local file system in the .scratch/ directory (SKILL.md).
Sanitization: There is no evidence of content sanitization or validation for the data retrieved from external trackers or documents.
[COMMAND_EXECUTION]: The skill uses the gh command-line tool to interact with GitHub Issues. While this is the intended purpose of the skill, the execution of shell commands based on task breakdown logic is a relevant capability to monitor.

to-tickets