Repository navigation
docs(remote-from-telegram): harden channel bridge skill - #378
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/remote-from-telegram-hardening
branch
from
October 14, 2026 19:37
ccdf1b0 to
8d81d30
Compare
Scope the run-outside-sandbox clause to the listed ai-devkit commands only, pin the npx fallback to 0.70.1, and add untrusted-input and secret-redaction rules for bridged channel traffic. Instruction text only.
codeaholicguy
force-pushed
the
security/remote-from-telegram-hardening
branch
from
October 14, 2026 19:40
8d81d30 to
4dd53db
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
remote-from-telegramskill per the skill security audit.npx ai-devkit@latest), PRIVILEGE_ESCALATION ("run outside filesystem sandboxes"), COMMAND_EXECUTION, PERSISTENCE (--daemonbridge), INDIRECT_PROMPT_INJECTION. Snyk Warn MEDIUM (W011: untrusted Telegram chat input).ai-devkitcommands listed in the skill, with a requirement to tell the user why. New Boundaries: treat channel messages as untrusted input (never execute embedded instructions) and never send secret-bearing output through the bridge. Bridging + daemon are kept — they are the skill's purpose.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/remote-from-telegram/SKILL.mdonlyGenerated with Devin