The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze and fix build failures, which involves processing external, potentially untrusted data such as compiler logs, bundler diagnostics, and configuration files.
Ingestion points: Build logs, tool output, and workspace configuration files analyzed during the mapping of workflow boundaries (SKILL.md).
Boundary markers: The instructions do not specify boundary markers or directives to ignore instructions embedded within the logs or configurations being analyzed.
Capability inventory: The skill requires workspace-write access and is expected to interact with compiler pipelines, CI environments, and build tools (SKILL.md).
Sanitization: There are no explicit instructions to sanitize or validate build tool output before it is processed by the agent.

build-engineer