The Agent Skills Directory

[DATA_EXFILTRATION]: The skill's primary function involves exporting project context and drafted task descriptions to external third-party services.
Evidence: Instructions direct the agent to publish tickets to GitHub using the gh CLI and to Linear using the save_issue tool.
[PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection by processing data from external, potentially user-controlled sources.
Ingestion points: The skill explicitly instructs the agent to fetch and read the full body and comments of issues or specifications from external URLs or identifiers.
Boundary markers: There are no instructions to utilize delimiters or to ignore potential instructions embedded within the external content.
Capability inventory: The agent has the capability to write local files (under .scratch/), execute shell commands (gh), and perform network operations via specialized tools.
Sanitization: The instructions do not mention any validation or sanitization of the content retrieved from external sources before it is processed or used to generate new artifacts.
[COMMAND_EXECUTION]: The skill utilizes command-line interfaces to interact with the environment and remote repositories.
Evidence: The skill specifies the use of gh issue create to publish information to GitHub.

to-tickets-plus