ecosystem-weaver
Self-improving /loop runbook that weaves the ruvnet package fabric. Each tick ingests lane reports into the weaver ledger, refreshes the package graph, repo scans, open PRs and release checks, ranks a one-lane-per-repo queue, and dispatches up to 8 lanes that integrate, fix, land, create and publish packages behind hard gates. Use for ecosystem cross-integration, release-regression repair, open-PR triage, and autopilot package creation across ruvnet repos.
91%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Medium
Suggest reviewing before use
W009: Direct money access capability detected (payment gateways, crypto, banking).
What this means
The skill is specifically designed for direct financial operations, giving the agent the ability to move money or execute financial transactions — such as payment processing, cryptocurrency operations, banking integrations, or market order execution.
Why it was flagged
The skill describes an autonomous ecosystem maintenance loop (`weaver`) that runs automated lanes to build, test, and publish packages to npm and crates.io (SKILL.md:4, SKILL.md:106-115). Although it fetches registry tokens securely via gcloud secrets at publish time (SKILL.md:133), the skill executes direct financial/monetization tasks (publishing software packages and managing releases without human approval for new creations) without an independent authentication or authorization control enforced by the service or execution layer for the action itself. Therefore, it is a direct operation without a qualifying independent access control.
W011: Third-party content exposure detected (indirect prompt injection risk).
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
The weaver CLI ingests open pull requests and repository scan results from GitHub, which are outsider-authored free text sources consumed by the workflow.
- Repository
ruvnet/RuVector
- Revision
f4ab6ce
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.