The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes data from the local repository, including source code and Architectural Decision Records (ADRs), which could contain adversarial instructions targeting the LLM. Ingestion points: Explore the repo, ADRs, and domain glossary as specified in SKILL.md. Boundary markers: Absent. The instructions do not specify delimiters for external content. Capability inventory: The skill is intended to read repository content and write a specification to an external issue tracker. Sanitization: Absent. No filtering or sanitization of ingested content is defined.
[NO_CODE]: The skill documentation and configuration do not include any scripts, executables, or dynamic code execution patterns.

to-spec