fix(ci): update Gemini model and harden update-skill against prompt injection - #991
Open
dkhawk wants to merge 5 commits into
Open
fix(ci): update Gemini model and harden update-skill against prompt injection#991dkhawk wants to merge 5 commits into
dkhawk wants to merge 5 commits into
Conversation
Contributor
Code Coverage
|
dkhawk
force-pushed
the
fix/update-skill-gemini-model
branch
from
September 4, 2026 19:54
27727a6 to
273cebc
Compare
dkhawk
marked this pull request as draft
September 4, 2026 19:58
dkhawk
marked this pull request as ready for review
September 8, 2026 17:07
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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 Gemini model in
.github/scripts/update_skill.pyto default togemini-3.8-flashand implements comprehensive hardening across.github/scripts/update_skill.pyand.github/workflows/update-skill.ymlto protect against indirect prompt injection and supply-chain tampering (referencing GHSA-8f2g-33j4-ghwg).Background & Vulnerability
External pull requests or commit messages in release diffs can contain adversarial prompt directives. If ingested unescaped, an attacker could manipulate
update_skill.pyinto injecting malicious instructions or compromised dependencies into.gemini/skills/android-maps-compose/SKILL.md.Hardening Measures Applied
system_instruction):system_instructionparameter to isolate operational rules and security boundaries from untrusted diff content.<current_skill_file>and<untrusted_release_diff>XML blocks and sanitizes potential delimiter escape sequences.git diffto code and build files only, explicitly excluding documentation (*.md,*.txt), images, and workflow files (.github/) where natural language injections typically hide.validate_skill_content):// x-release-please-version).automergelabel so AI-generated skill updates always require maintainer approval.peter-evans/create-pull-requestto create draft PRs with required reviewers (LoyalAbbas,kikoso).googlemaps-bot@users.noreply.github.com.__pycache__/,*.py[cod]) to.gitignore.