The Agent Skills Directory

[DATA_EXPOSURE] (SAFE): The skill handles data context but does not reference sensitive system paths, hardcoded credentials, or unauthorized external network endpoints.
[REMOTE_CODE_EXECUTION] (SAFE): No remote code execution patterns, package installations, or piped shell commands were found. The included TypeScript snippets are instructional logic for the agent's behavior and are not executed in an unsafe runtime context.
[INDIRECT_PROMPT_INJECTION] (LOW): The skill is designed to ingest and process data from other agents (DAG nodes).
Ingestion points: dependencies: NodeContext[] in SKILL.md.
Boundary markers: None explicitly defined in the provided snippets.
Capability inventory: File system access via Read, Write, Edit, Glob, and Grep.
Sanitization: Not explicitly defined. While the skill processes potentially untrusted data from other agents, its primary role is summarization and routing, posing a low risk typical of orchestration tools.

dag-context-bridger