The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill operates by fetching and processing data from an external issue tracker, which serves as an ingestion point for untrusted content. Malicious instructions placed in issue bodies or comments could potentially influence the agent's planning logic or behavior. \n- Ingestion points: The agent is instructed to fetch the map body and zoom into specific ticket bodies and comments from the issue tracker. \n- Boundary markers: The skill does not define any specific delimiters or instructions to help the agent isolate and ignore potential instructions embedded in the ingested data. \n- Capability inventory: The skill enables the agent to create and modify issues, assign users, and invoke other sub-agents for research or prototyping. \n- Sanitization: No sanitization or validation logic is specified for the data retrieved from the tracker before it is processed by the agent.

wayfinder