The Agent Skills Directory

[DYNAMIC_EXECUTION]: The skill incorporates a mechanism to load instructions from a dynamically determined path via the $POWERSUIT_OVERLAY environment variable. It instructs the agent to check this path, read README.md and other files within sdlc/ticket/, and follow those instructions even where they conflict with the primary skill instructions. This allows for runtime modification of the agent's behavior based on environment configuration.
[COMMAND_EXECUTION]: The skill uses the GitHub CLI (gh) to perform operations such as listing issues, creating issues, and creating labels. It also executes shell commands to check for the existence of overlay directories (ls -1). While these are functional requirements, they represent the execution of shell commands based on internal logic.
[INDIRECT_PROMPT_INJECTION]: The skill has a defined surface for indirect prompt injection as it ingests untrusted data from external sources.
Ingestion points: The skill reads content from "a request, a bug report, a chat or a postmortem action item" as specified in the description and SKILL.md.
Boundary markers: There are no instructions for using delimiters or boundary markers to separate user-provided content from the agent's instructions.
Capability inventory: The skill possesses capabilities to write to the file system (gh issue create --body-file) and interact with remote APIs via gh issue and gh label commands.
Sanitization: There are no explicit instructions for sanitizing or escaping the external content before it is processed or used to generate ticket bodies.

ticket