The Agent Skills Directory

[PROMPT_INJECTION]: The skill is susceptible to Indirect Prompt Injection because it ingests and acts upon content from an external issue tracker (titles, bodies, and comments) which can be influenced by external actors. * Ingestion points: Issue bodies and comments from the repository's tracker. * Boundary markers: Absent. * Capability inventory: Issue creation, assignment, closing, and subagent invocation. * Sanitization: Absent.
[CREDENTIALS_UNSAFE]: Instructions for "Task" resolution advise the agent to record findings like "credentials location" in issue comments, which may expose sensitive information in shared environments.
[COMMAND_EXECUTION]: The documentation references an external setup command /setup-matt-pocock-skills to be run by the user, which introduces an external dependency.

wayfinder