The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill instructions require the agent to ingest and act upon data from external files and ticket trackers, creating a surface for indirect prompt injection where malicious instructions could be embedded in those sources.
Ingestion points: The agent is instructed to read the ticket, approved spec, CONTEXT.md, docs/glossary.md, ADRs, and repository instructions as part of its workflow defined in SKILL.md.
Boundary markers: There are no explicit instructions or delimiters defined to help the agent distinguish between data and instructions within these ingested sources.
Capability inventory: The agent has the capability to modify repository code and execute shell commands related to development workflows, such as typecheck, lint, build, and test commands as specified in SKILL.md.
Sanitization: There are no requirements for sanitizing or validating the content of the tickets or specifications before they are processed by the agent.

implement