The real workflow
Where Perplexity enters the work
Agency teams may connect several client mailboxes, drives, knowledge sources, and project systems to a common assistant workflow.
Perplexity combines AI search with conversations, uploads, projects or spaces, and optional organizational repositories or connectors depending on plan.
Search results, webpages, uploaded documents, and connected files can carry instructions that should not control the assistant.
The risk depends on what is searched, uploaded, retained, shared, or connected. Consumer and Enterprise data controls are materially different and should not be assumed equivalent.
The presence of this path does not prove an incident. It identifies the boundary that should be checked before more sensitive context or authority is added.
Tool-specific boundary
Inspect the real access points.
What may carry context
search queries and conversation history
uploaded files and projects
connected storage and organizational repositories
Settings to verify
AI Data Retention or training choice
Library, projects, and shared sessions
File, connector, and organization permissions
Why this context matters
The consequence for agencies
Agency risk compounds when staff, contractors, shared tools, and reused credentials create paths between otherwise separate client environments. In this case, in connected workflows, the same manipulation can influence code, messages, documents, tickets, cloud actions, or data transfer across trusted systems.
Prompt injection happens when untrusted content contains instructions that compete with the user’s real request. The danger rises when the assistant can retrieve private information, call tools, run commands, or make changes.
Every client remains isolated, access is attributable to a named operator, and the agency can deliver consistent evidence without revealing another client.
Context decision
Three questions before adding access
Can this operator or tool reach any repository, mailbox, drive, cache, token, or transcript belonging to another client?
Are credentials and AI sessions issued per client and person rather than shared across the agency?
Can the agency deliver useful proof to this client without including another client's names, paths, findings, or configuration?
Evidence goal: Create a separate client evidence record covering operator identity, workspace isolation, credentials, approved systems, review history, and delivery status.
A repeatable review
Four steps, no sensitive data required
- 1
Write down the exact Perplexity account, workspace, project, device, and connected service used in this workflow.
- 2
Compare claims with cited sources and keep untrusted research separate from action-capable tools.
- 3
Assign the decision and next review to the client service owner or agency security lead; do not leave the access boundary as an unwritten assumption.
- 4
Do not copy commands or authorization instructions from retrieved content without independent review. Record the result without copying private content or raw credentials into the report.
Controls to apply
Reduce access before adding trust
Do not copy commands or authorization instructions from retrieved content without independent review.
Separate trusted instructions from retrieved or user-supplied content.
Use tool allowlists, denied paths, network restrictions, and approval gates around consequential actions.
Log the source of instructions and stop when tool behavior changes unexpectedly.
Decision rule
Know when a formal baseline is justified
Simple text-only use still needs judgment, but the paid security case begins when untrusted content and meaningful tool authority coexist. That is the point to map the full action-to-asset path.
CapitalGuard is relevant when the workflow includes repositories, recurring private work, credentials, connected systems, commands, or evidence that must be shared with another person. It does not inspect this account from the page or guarantee that an incident cannot occur.
Primary references