Notifications
Clear all
Topic starter
01/08/2026 10:47 pm
TL;DR: AI agent telemetry only becomes useful when identity, host, and session context are stitched together before analysts can see abuse. Claude Code and Cowork emit OpenTelemetry events that can be parsed, reduced, redacted, and correlated for detections across prompts, tools, MCP activity, and suspicious execution patterns, according to Abstract Security.
NHIMG editorial — based on content published by Abstract Security: Security Claude Code and Cowork monitoring for threat detection and visibility in the SOC
By the numbers:
- When AWS credentials are exposed publicly, attackers attempt access within an average of 17 minutes , and as quickly as 9 minutes in some cases.
Questions worth separating out
Q: How should security teams monitor AI coding agents without overwhelming the SOC?
A: Focus on session-level correlation, not raw event volume.
Q: Why do AI agents create a visibility problem for IAM teams?
A: AI agents often appear outside formal onboarding through shadow AI, scripts, or workflow tools, so they never enter the normal identity inventory.
Q: What breaks when prompt logs are stored without redaction?
A: You create a privacy and secrets exposure problem inside your security telemetry.
Practitioner guidance
- Preserve session lineage in the log schema Retain session.id, prompt.id, and event_sequence in the ingestion pipeline so analysts can reconstruct a complete agent interaction rather than isolated events.
- Enable detailed tool logging by default Keep tool-level fields such as file paths, shell commands, MCP server details, and hook metadata available for security review instead of relying on minimal event summaries.
- Apply prompt redaction before storage Mask secrets, SSNs, and other sensitive strings in prompt and tool input events before they reach long-term retention, especially where shared analytics access exists.
What's in the full article
Abstract Security's full post covers the operational detail this post intentionally leaves for the source:
- Step-by-step Claude Code and Cowork ingestion configuration for the Abstract Forwarder and OTLP receiver
- Pipeline examples for event dropping, aggregation, and deduplication to reduce log volume by 30% to 50%
- Detection logic for secret leakage, PII redaction, and trust-prompt abuse patterns
- Correlation setup that ties agent events to endpoint process activity on the same host
👉 Read Abstract Security's analysis of Claude Code and Cowork threat detection and monitoring →
Claude Code and Cowork visibility gaps: what SOC teams need now?
Explore further
01/08/2026 10:55 pm
Claude Code and Cowork monitoring is an identity governance problem before it is a logging problem. The article makes clear that useful detection depends on preserving session lineage, prompt context, and tool execution detail. Without those identity links, the SOC is left with telemetry fragments that cannot support investigation or policy enforcement, which means the logging design itself becomes part of the control plane.
A few things that frame the scale:
- Only 1.5 out of 10 organisations are highly confident in their ability to secure NHIs, compared to nearly 1 in 4 for securing human identities, according to The State of Non-Human Identity Security.
- Lack of credential rotation is cited as the top cause of NHI-related attacks by 45% of organisations, followed by inadequate monitoring and logging at 37% and over-privileged accounts at 37%.
A question worth separating out:
Q: Who is accountable when an AI agent takes action through an MCP server?
A: The accountable party is the human or team that authorised the agent's access, but only if the organisation can prove that chain. Without immutable logs that connect the initiating identity to the tool call and final action, accountability becomes weak, and legal or compliance teams lose the evidence they need.
👉 Read our full editorial: Claude Code and Cowork monitoring exposes the agent logging gap
