The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill instructions require the agent to fetch and process data from external issue trackers and user-provided specifications, creating a surface for indirect prompt injection where malicious instructions could be embedded in ticket content.
Ingestion points: External ticket content fetched from issue trackers and work specifications provided by users, as defined in SKILL.md.
Boundary markers: The instructions lack explicit requirements for the agent to use delimiters or to disregard instructions contained within the external ticket data.
Capability inventory: The skill is authorized to modify source code, execute testing workflows via matt-tdd, perform code reviews via matt-code-review, and commit changes to the version control system.
Sanitization: There is no evidence of sanitization or validation protocols for the data retrieved from external trackers before it influences the implementation logic.

matt-implement