Summary Authorization for scoped (agent) MCP callers is enforced inline, per tool, and is applied inconsistently — several mutating tools silently omit the ancestry/workspace check that their siblings perform. Because the MCP server authenticates all outbound gRPC with the full s...
Product
grackle-ai @grackle-ai/plugin-core vulnerabilities
1 published CVE affecting grackle-ai @grackle-ai/plugin-core, from public sources (CVE.org, NVD, CISA KEV, FIRST EPSS, OSV).
- Total
- 1
- Critical
- 0
- High
- 1
- Medium
- 0
- Low
- 0
- Unscored
- 0
- CISA KEV
- 0
Latest grackle-ai @grackle-ai/plugin-core CVEs
Newest publication first
-
HighCVSS 8.7
Sources: CVE.org, NVD, CISA KEV, FIRST EPSS, OSV and public exploit-reference metadata. Product matching comes from the published CVE records. A proof-of-concept means public code exists; it is not evidence of exploitation.