The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external sources that are not fully controlled by the user, creating a surface for indirect prompt injection.
Ingestion points: As described in Step 1 of the Process, the skill fetches and reads the full body and comments of external issue URLs or numbers, and in Step 2, it reads from the local codebase.
Boundary markers: The instructions do not define clear delimiters or instruct the agent to ignore potentially malicious instructions embedded within the external context it gathers.
Capability inventory: The skill has the capability to write files to the local filesystem (under the .scratch directory) and perform network operations by publishing tickets to real issue trackers (GitHub, Linear).
Sanitization: There is no evidence of sanitization or filtering applied to the gathered content before it is used to generate ticket titles, descriptions, and acceptance criteria.
[COMMAND_EXECUTION]: The skill instructs the agent to invoke specific slash commands, which represent a dependency on other platform tools or skills.
Evidence: The skill mentions running /setup-matt-pocock-skills for configuration and using /implement to process the generated tickets. While these are part of the intended workflow, they represent the execution of external logic within the agent's environment.

to-tickets