Notifications
Clear all
Topic starter
01/08/2026 10:48 pm
TL;DR: Straiker’s assessment of Emergent’s Wingman shows that connected AI agents can be pushed into unauthorized actions through untrusted content, cross-connector flows, and scheduled persistence, even when users never intended those side effects. The real control problem is provenance, flow restriction, and approval, not model confidence alone.
NHIMG editorial — based on content published by Straikerai covering Emergent's Wingman connected agent threat model: Threat Modeling a Connected Agent: Red Teaming Emergent's Wingman
Questions worth separating out
Q: How should security teams manage permissions for AI agents?
A: Security teams should regularly assess and update the permissions granted to AI agents to ensure they align with their intended scope.
Q: Why do AI agents create more risk than traditional automation?
A: AI agents create more risk because they can interpret context, choose actions, and invoke tools autonomously.
Q: What do security teams get wrong about prompt engineering for AI agents?
A: They often assume better wording is enough to create reliable control.
Practitioner guidance
- Implement provenance-aware policy checks Classify every inbound artifact by source trust before it can influence tool use, scheduling, or outbound communication.
- Constrain cross-connector authority Review every read-from-one-system and write-to-another flow against user intent, data sensitivity, and destination trust.
- Gate scheduled tasks as privileged actions Treat recurring jobs, delayed follow-ups, and background runs as separate approval points with stronger logging and replayable tests.
What's in the full article
Straiker's full post covers the operational detail this post intentionally leaves for the source:
- Concrete attack-path examples across email, documents, calendars, repositories, social messages, and browser workflows
- Detailed control classes for provenance, confirmation, sandboxing, and cross-connector policy decisions
- Evaluation guidance for testing tool calls, writes, deletes, scheduled jobs, and final workspace state
- Companion post references that explain how the vendor hardened Wingman before launch
👉 Read Straiker's analysis of connected agent threat modeling and Wingman →
Connected AI agents: are your controls keeping up?
Explore further
01/08/2026 10:56 pm
Policy must govern the flow, not the model prompt: this article shows that connected agents fail when security treats model output as the decision point. The real issue is whether source content is allowed to influence a downstream action across connectors, schedules, and browsers. That makes provenance, intent, and destination policy the governing controls, not prompt hygiene alone. For identity teams, this is the clearest sign that agent permissions need lifecycle controls as strict as human and workload access.
A question worth separating out:
Q: Who is accountable when an AI agent makes an unauthorised change?
A: Accountability should be assigned to the governance model that authorised the delegation, the owner of the workflow, and the team that set the policy boundary. In practice, organisations need clear responsibility for agent configuration, monitoring, and incident response because the machine’s speed does not remove human accountability for the delegated identity.
👉 Read our full editorial: Connected AI agents need policy controls beyond model prompts
