The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted content from external GitLab issues and user-provided text.
Ingestion points: The skill fetches issue titles, descriptions, and the entire comment thread history using the read_issue and list_issue_comments tools as described in Phase 1 of SKILL.md.
Boundary markers: The instructions do not specify the use of delimiters or boundary markers to isolate untrusted external content from the agent's internal reasoning or instructions during processing.
Capability inventory: The agent has the capability to write back to external GitLab issues using the add_issue_comment tool and read various local project documentation files, such as docs/context/brownfield-map.md and architecture-rules.md (SKILL.md, Phase 2 and 4).
Sanitization: No explicit sanitization, filtering, or validation of the content fetched from GitLab is performed before the data is synthesized into summaries and new comments.

ns-requirements-enricher