The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external sources including git logs, file diffs, project plans, and task boards. This represents a potential surface for indirect prompt injection, where malicious instructions embedded in these external files could attempt to influence the agent's behavior during the briefing process. • Ingestion points: SKILL.md specifies reading live state from git log/diffs, plan and state docs, re0-memo notes, and task boards. • Boundary markers: The instructions do not specify the use of delimiters or boundary markers to encapsulate external content and prevent the agent from following instructions contained within that data. • Capability inventory: The skill is explicitly defined as read-only and informative, stating it 'briefs, it does not act', which limits the immediate impact of an injection. • Sanitization: The skill does not mention sanitizing or filtering external content before processing.

catchup