registry: add solana-agent-transaction-safety skill - #23
Open
Alb3e3 wants to merge 1 commit into
Open
Conversation
|
@Alb3e3 is attempting to deploy a commit to the STBR TRUE Team on Vercel. A member of the Team first needs to authorize it. |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What
Adds a registry entry for solana-agent-transaction-safety, a pre-sign transaction safety skill for AI agents, backend signers, wallet flows, simulations, swaps, Token-2022 operations, authority changes, CPIs, and autonomous signing policies.
Repo: https://github.com/Alb3e3/solana-agent-transaction-safety
Why it is net-new
The kit already has strong build, audit, security-watch, and counterparty-risk coverage. This skill targets a different boundary: the concrete transaction immediately before signing. It classifies a transaction plan or decoded transaction as
AUTONOMOUS_OK,CONFIRM_REQUIRED,NEVER_AUTO_SIGN, orNEEDS_MORE_INFObased on intent, simulation, account deltas, authority risk, DeFi/swap risk, and policy limits.This is meant to stop blind agent signing: simulation success is evidence, not approval.
What is inside
skill/SKILL.mdprogressive router./tx-safety-reviewcommand spec.transaction-safety-revieweragent prompt.no-blind-signingcompact rule.NEVER_AUTO_SIGN,CONFIRM_REQUIRED, andAUTONOMOUS_OK.Safety
MIT. Markdown skill plus a copy-only installer. No network installer, hooks, telemetry, runtime API key, or opaque executable. CI runs the smoke checks and installer dry run.
Verification
Skill repo:
bash tests/smoke.shbash -n install.sh tests/smoke.shquick_validate.py skill.claude/projectSolana AI Kit branch:
python3 -m json.tool .claude/skills/skill-registry.jsonbash validate.shbash tests/test_skills.shbash tests/run_all.shSubmitted for the Superteam Earn "Ship useful agent skills we can add to Solana AI Kit" bounty.