The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process potentially untrusted data from external sources such as call transcripts, customer evidence, and uploaded competitor documents to populate competitive battlecards.
Ingestion points: The skill retrieves data from call transcripts and deal events using search_call_transcripts and get_event_detail as described in references/task-method.md. It also searches external resources like analyst reports via search_resources in references/tool-reference.md.
Boundary markers: The instructions do not explicitly mandate the use of delimiters or instructions for the agent to ignore potential injections within the retrieved text from these external sources.
Capability inventory: The skill generates HTML and text artifacts and performs extensive data retrieval operations across the workspace.
Sanitization: There is no explicit requirement for the agent to sanitize or escape the content fetched from transcripts or external documents before it is interpolated into the final output.

battlecard-doc