The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests and processes data from external sources that could potentially contain malicious instructions designed to influence the agent's behavior.
Ingestion points: Results from search, transcripts from meeting_lookup, and synthesized content from the chat tool and project-synthesizer agent.
Boundary markers: Absent; the instructions do not include specific delimiters or warnings to the agent to ignore instructions embedded within the retrieved project data.
Capability inventory: The skill utilizes information retrieval and synthesis tools (search, meeting_lookup, employee_search, chat, project-synthesizer) to build the handoff document.
Sanitization: Absent; there is no evidence of content validation or sanitization of the retrieved data before it is presented to the user or processed further.

project-handoff