The Agent Skills Directory

Indirect Prompt Injection Surface: The skill facilitates the aggregation of data from external sources such as chat logs and project trackers. While this is the intended purpose, it is a common security consideration to include clear boundary markers when processing external data to ensure the agent focuses on summarization rather than any instructions that might be embedded in the source content. The skill currently focuses on text generation and does not have access to sensitive system operations. (1) Ingestion points: The integration with external trackers and chat history specified in SKILL.md. (2) Boundary markers: None explicitly defined in the output template. (3) Capability inventory: The skill is restricted to generating markdown output. (4) Sanitization: Content is processed directly from the connected tools.

status-report