TL;DR: Unattended local execution is the central risk, with Repello AI's analysis showing that claude --dangerously-skip-permissions removes Claude Code's per-action approval layer. Endpoint transcripts, process arguments, and git history become the evidence trail, so cloud logs alone cannot reconstruct what changed.
Editorial analysis by NHI Mgmt Group, based on content published by Repello AI: “--dangerously-skip-permissions: A 5-Minute Triage Runbook”.
Key questions
Q: Why do local session transcripts matter more than cloud audit logs for AI coding agents?
A: Cloud logs usually show request timing and usage metadata, but not the commands, paths, or files the agent touched.
Q: What are the signs that a developer workstation agent is operating outside its intended boundary?
A: Look for the flag in process telemetry, shell aliases, setup scripts, or CI steps, especially when it appears without a sandbox guard such as IS_SANDBOX.
Q: What breaks when a coding agent runs without per-action approval?
A: The control that breaks is not code safety but runtime authorisation.
Practitioner guidance
- Block the skip-permissions flag at the organisation level Use managed settings to disable bypass permissions mode so the CLI refuses the flag at startup, then test unmanaged installs to confirm the block survives local workarounds.
- Search endpoints for unattended agent use Look for the literal flag string in process command lines, shell history, CI job logs, and setup scripts, because that is the fastest way to identify where agent execution was made unattended.
- Preserve the local session corpus Collect ~/.claude/projects/ session JSONL files, because they contain the tool-use transcript needed to reconstruct file writes, shell commands, and MCP activity after the fact.
Bottom line: The central risk is unattended local execution, not model autonomy, because the flag removes the approval gate that normally constrains each tool call.
Glossary terms: Unattended Execution, Session Transcript, MCP Server Registration, Managed Settings
Explore further
View Full Forum → | NHI Foundation Course → | Our Services → | Read the full analysis →
Unattended agent execution is a governance problem before it is an AI problem. The flag turns a chat-based tool into an endpoint actor that can write files, run commands, and invoke MCP tools without per-action consent. That shifts the security question from model behaviour to delegated authority and local blast radius. Organisations that still treat this as a novelty risk are behind the actual control failure, which is runtime authorisation on the workstation.
A few things that frame the scale:
- Claude Code-assisted commits leaked secrets at a rate of 3.2%, more than double the human-only baseline of 1.5%, with peaks reaching 31 secrets per 1,000 commits in August 2025, according to the State of Secrets Sprawl 2026.
- 24,008 unique secrets were exposed in MCP configuration files in 2025 alone, the protocol's first year of widespread adoption, according to the State of Secrets Sprawl 2026.
A question worth separating out:
Q: Should organisations rely on auto mode instead of blocking risky agent flags?
A: No. Auto mode reduces the chance of obvious destructive actions, but it does not remove the underlying need for policy enforcement, endpoint detection, and transcript collection. Organisations should use it as a safer default while still disabling bypass modes and monitoring for unmanaged installs. Otherwise, the risky path remains available whenever a developer chooses it.
👉 Read our full editorial: Claude Code’s skip-permissions flag creates an unattended write window