Skip to content

claude-code adapter: pass --dangerously-skip-permissions #2

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
gabehamilton wants to merge 2 commits into
base: main
Choose a base branch
from
Open

claude-code adapter: pass --dangerously-skip-permissions #2

Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
261accf
claude-code adapter: pass --dangerously-skip-permissions
gabehamilton May 21, 2026
0cd4fa3
Make skip-permissions opt-in via AgentRunOptions::auto_approve_tools
gabehamilton May 21, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
7 changes: 6 additions & 1 deletion crates/forge-llm/src/cli_adapters/claude_code.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -44,7 +44,12 @@ impl ClaudeCodeAgentProvider {
.arg(prompt)
.arg("--output-format")
.arg("stream-json")
.arg("--verbose");
.arg("--verbose")
// The spawned session has stdin=null so it cannot answer
// permission prompts. Without this flag every tool call gets
// silently denied and the stage degenerates into "partial_success
// with N tool errors" without actually doing work.
.arg("--dangerously-skip-permissions");
Copy link
Copy Markdown

@gemini-code-assist gemini-code-assist Bot May 21, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

security-medium medium

Bypassing all permission prompts with --dangerously-skip-permissions is a significant security risk, as it allows the LLM to execute potentially destructive tools (such as shell commands or file writes) without human oversight. While this is necessary for non-interactive execution when stdin is null, it should ideally be an opt-in configuration. Consider adding a field to AgentRunOptions to allow users to explicitly enable this behavior, or at least ensure this security trade-off is prominently documented for users of this provider.

Copy link
Copy Markdown
Author

@gabehamilton gabehamilton May 21, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Fixed in 0cd4fa3. Made it opt-in: added auto_approve_tools: bool to AgentRunOptions (defaults to false). ClaudeCodeAgentProvider only passes --dangerously-skip-permissions when that flag is true. The forge-attractor AgentProviderSubmitter (used by pipeline runs where stdin=null is the design) sets it to true; library consumers wiring up AgentProvider directly now have to make an explicit choice. Doc comment on the field explains the trade-off.


let model = options
.model_override
Expand Down