Document security fix for subagent tool privilege escalation - #102
Merged
Conversation
Rafael Asor (Attenu) reported the subagent privilege escalation privately and asked to be credited as "Rafael Asor (Attenu)" with a link to attenu-guard. Also records that no released version was affected. v1.2.0 was tagged at 07:49 on 3 September and the delegation tool landed at 16:17 the same day, so the issue existed only on main, between a5a401c and the fix. Anyone running a release was never exposed, and a changelog entry that leaves that unsaid reads as though they were. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01ToCUNy2SqwvfTq4a6xfSk1
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Updates the CHANGELOG to document a critical security vulnerability fix and credit the reporter. The issue involved subagents being able to exceed their parent agent's tool privileges through prompt injection, potentially granting access to dangerous tools like
execute_shell_command,delete_agent, andplace_order.Changes
main.Details
The fix itself (tool intersection logic in
_build_subagent_tools) was already implemented. This change documents:mainonlyThis improves transparency and gives proper credit to the security researcher who responsibly disclosed the vulnerability.
https://claude.ai/code/session_01ToCUNy2SqwvfTq4a6xfSk1