Repository navigation
docs(agent-communication): guard piped output and inbound messages - #385
Closed
codeaholicguy wants to merge 1 commit into
Closed
codeaholicguy wants to merge 1 commit into
codeaholicguy wants to merge 1 commit into
Conversation
codeaholicguy
force-pushed
the
security/agent-communication-pipe-guard
branch
from
October 14, 2026 19:37
ef68e0e to
b023cc4
Compare
Forbid piping secret-bearing output to other agents, require redaction, and mark messages from other agents as untrusted data. Pin npx fallback to 0.70.1. Instruction text only.
codeaholicguy
force-pushed
the
security/agent-communication-pipe-guard
branch
from
October 14, 2026 19:40
b023cc4 to
8a0af9c
Compare
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Hardens the
agent-communicationskill per the skill security audit.<command> 2>&1 | ai-devkit agent send --stdinforwards arbitrary command output to other agents, which can propagate secrets or carry injected instructions agent-to-agent (same W007/W011 surface skills.sh flagged on verify/remote-from-*). skills.sh audits: Pass ×3.npx ai-devkit@latestfallback to barenpx ai-devkit— prefers an installed binary (zero network when present), fetches only when absent; avoids both@latestbypass and pin staleness.Test plan
skills/agent-communication/SKILL.mdonlyGenerated with Devin