Trust and health report
agent - trust report
Sourced, dated trust signals - maintenance label posture, repository provenance, and security scan status. Not a composite safety grade.
GraphCanon updated today · GitHub synced today
Maintenance
Recency and activity heuristics from public GitHub metadata (maintenance label, momentum); methodology: github_public_v1.
last push 5d ago · last release 5d · 3 releases (90d)
Provenance
Repository identity and fork provenance (github_public_v1).
- GitHub repo id: 1265780842
- Not a fork
- Personal account
- Computed today
Security scan
Manifest-only review of declared MCP transports and auth fields. Not a full code audit.
- Status
- 1 medium
- Last scan
- today
- Scanner
- mcp_manifest@v1
Findings
Method and caveats:these are sourced, dated heuristics from public GitHub data and optional dependency scans. A status like "no criticals found on 2026-07-11" is not a guarantee of safety. Read the full trust methodology · JSON report at /api/graphcanon/tools/taisly-agent/trust.
Common questions
- Is agent maintained?
- GraphCanon rates agent "Very active" (96% maintenance signal from public GitHub metadata, computed today). Last push was 5 days ago. 3 GitHub releases in the last 90 days. This is a recency heuristic, not a guarantee the project will stay maintained.
- Is agent safe to use?
- Last scanned today (mcp_manifest profile). Status: 1 medium - 1 medium finding(s) in the latest scan. GraphCanon does not claim the project is safe or vulnerability-free; review findings on the trust report. GraphCanon does not certify agent as safe - review maintenance, provenance, and scan findings on this page before adopting.
- Is agent a fork?
- No. agent is not flagged as a fork in GitHub metadata at the time of the last refresh.
- Does agent have known security vulnerabilities?
- Last scanned today (mcp_manifest profile). Status: 1 medium - 1 medium finding(s) in the latest scan. GraphCanon does not claim the project is safe or vulnerability-free; review findings on the trust report.
- How often is the agent trust report updated?
- Trust signals refresh on GitHub ingest/refresh cycles and optional dependency/MCP scans. This report was computed today (methodology github_public_v1).
- What does GraphCanon never claim about agent?
- We never publish a composite safety grade, pen-test endorsement, or "verified secure" label for agent. Signals are sourced heuristics with explicit limits - see trust methodology.
- How does GraphCanon assess trust for agent?
- Signals are sourced from public GitHub metadata and optional dependency/MCP manifest scans, each tagged with methodology version and computed date. GraphCanon does not publish a composite safety grade. Read trust methodology for full scope and limits.