The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external data such as sprint backlogs, team metrics, and project documentation, which creates a potential surface for indirect instructions to influence agent behavior.
Ingestion points: Sprint artifacts, product backlogs, and user-provided agility data processed via Read, Grep, and Glob tools.
Boundary markers: Absent. The instructions do not define explicit delimiters or 'ignore' instructions to isolate processed data from the core system prompt.
Capability inventory: The agent is granted Write and WebSearch capabilities, which could be potentially misused if the ingested data contains hidden instructions.
Sanitization: Absent. The instructions do not specify validation or sanitization steps for the external content before analysis.

scrum-sage