The Agent Skills Directory

[SAFE]: The skill defines a standard verification workflow for confirming that technical implementations meet discovery goals. All identified operations use internal project tooling for artifact management and codebase inspection.
[INDIRECT_PROMPT_INJECTION]: The skill processes data from artifacts like feature-context and architect, which are external ingestion points.
Ingestion points: Artifacts are retrieved using artifact_read and sam_task (read mode) in SKILL.md.
Boundary markers: None explicitly defined; the agent is instructed to extract specific named sections.
Capability inventory: Capabilities include codebase read access and updating plan tasks via sam_task update actions. No network access or arbitrary code execution capabilities are present.
Sanitization: No content sanitization is mentioned for the ingested artifact content.

final-verification