The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process potentially untrusted data to generate output for an external issue tracker.
Ingestion points: Reads the current conversation context and performs repository exploration to understand the codebase state (SKILL.md).
Boundary markers: Uses a structured <spec-template> for its output, but lacks explicit instructions to ignore or escape malicious prompts embedded within the processed conversation or code files.
Capability inventory: The skill has the capability to explore the repository (read access) and publish content to an external project issue tracker (write access).
Sanitization: There is no explicit sanitization or filtering logic mentioned for the content extracted from the codebase or conversation before it is published to the issue tracker.
[EXTERNAL_DOWNLOADS]: The skill references an external source for its configuration and potential setup.
The .provenance file indicates the source is the mattpocock/skills repository on GitHub.
The instructions mention a setup command /setup-matt-pocock-skills which likely configures the environment or triage labels from this external source.

to-spec