OWASP MCP Top 10 — Compliance Assessment
2025 · 2026-04-23 registry entry
Executive summary
✗ Non-compliant
Assessment of GitHub Stars against OWASP MCP Top 10: overall status non compliant. Of 10 controls, 0 met, 2 unmet, 0 partial, 8 not assessed, 0 not applicable. 2 control(s) had complete mapped-assessor execution evidence; 8 lacked sufficient execution evidence and 0 were outside the current assessor mapping. Unmet controls have findings at or above the framework's mandatory severity threshold and should be remediated before relying on this server in a regulated deployment. All claims are traceable to individual finding rows via finding_id and to the governing rule via rule_id; the enclosing signed envelope commits MCP Sentinel to the exact bytes of this report.
Coverage & transparency
- Coverage band
- minimal
- Coverage ratio
- 6%
- Rules version
- 2026-04-23
Analysis techniques applied:
- composite
- dependency-audit
- similarity
- structural
Controls (10)
| ID | Control | Status | Evidence |
|---|---|---|---|
| MCP01 | Prompt Injection | ? Not assessed | 0 |
| MCP02 | Tool Poisoning | ✗ Unmet | 1 |
| MCP03 | Command Injection | ? Not assessed | 0 |
| MCP04 | Data Exfiltration | ? Not assessed | 0 |
| MCP05 | Privilege Escalation | ? Not assessed | 0 |
| MCP06 | Excessive Permissions | ? Not assessed | 0 |
| MCP07 | Insecure Configuration | ? Not assessed | 0 |
| MCP08 | Dependency Vulnerabilities | ? Not assessed | 0 |
| MCP09 | Logging & Monitoring Failures | ? Not assessed | 0 |
| MCP10 | Supply Chain Compromise | ✗ Unmet | 1 |
Control details
MCP01 — Prompt Injection
? Not assessed0/24 mapped assessor rule(s) are proven to have executed; no adverse findings were observed, but the control is not assessed because execution evidence is incomplete. Unexecuted assessors: A1 (execution-ledger); A5 (execution-ledger); A7 (execution-ledger); A8 (execution-ledger); A9 (execution-ledger); B5 (execution-ledger); F1 (execution-ledger); F6 (execution-ledger); G1 (execution-ledger); G2 (execution-ledger); G3 (execution-ledger); G4 (execution-ledger); G5 (execution-ledger); H2 (execution-ledger); H3 (execution-ledger); I3 (execution-ledger); I6 (execution-ledger); I7 (execution-ledger); J3 (execution-ledger); J5 (execution-ledger); J6 (execution-ledger); N4 (execution-ledger); N9 (execution-ledger); N12 (execution-ledger).
Control text:
Attacker-controlled content delivered through MCP server descriptions, parameters, resources, prompts, or initialize metadata that hijacks agent reasoning. Includes direct and indirect injection.
MCP02 — Tool Poisoning
✗ Unmet0/15 mapped assessor rule(s) are proven to have executed; 1 finding(s) observed (1 critical); at least one finding is at or above the high threshold (status: unmet). 15 mapped assessor(s) did not execute, so this finding-backed result does not imply complete control coverage.
Control text:
Tools that misrepresent their behaviour through deceptive names, annotations, namespace squatting, homoglyphs, or time-based drift (rug pulls).
- Critical Official Namespace Squatting (finding 2c2c43e6-03c7-4c7b-a6c8-318606fb49f7, confidence 90%) SOURCE: external-content at initialize.server_name — The MCP client surfaces the server name verbatim in its approval dialog, and the LLM ingests the server name alongside the tool descriptions. A nam
- If you own the server and are NOT affiliated with the vendor whose namespace it contains, rename the server to remove the vendor token. Choose a name that makes your actual publisher identity clear. If you ARE a vendor-approved partner and intentionally use the vendor's namespace, request inclusion in the rule's OFFICIAL_NAMESPACES.verified_github_orgs list by publishing the server under a vendor-sanctioned GitHub organisation. Users deciding whether to approve the server should check the repository owner against the vendor's published list of approved partners before granting trust.
MCP03 — Command Injection
? Not assessed0/6 mapped assessor rule(s) are proven to have executed; no adverse findings were observed, but the control is not assessed because execution evidence is incomplete. Unexecuted assessors: C1 (execution-ledger); C9 (execution-ledger); C13 (execution-ledger); C16 (execution-ledger); J2 (execution-ledger); J7 (execution-ledger).
Control text:
Server code that executes shell commands, system calls, or git operations built from attacker-controlled input without sanitisation.
MCP04 — Data Exfiltration
? Not assessed0/15 mapped assessor rule(s) are proven to have executed; no adverse findings were observed, but the control is not assessed because execution evidence is incomplete. Unexecuted assessors: A3 (execution-ledger); F1 (execution-ledger); F3 (execution-ledger); F7 (execution-ledger); G7 (execution-ledger); I9 (execution-ledger); I13 (execution-ledger); K18 (execution-ledger); O4 (execution-ledger); O5 (execution-ledger); O6 (execution-ledger); O8 (execution-ledger); O9 (execution-ledger); O10 (execution-ledger); P3 (execution-ledger).
Control text:
Server features that permit sensitive data to leave the trust boundary via HTTP, DNS, headers, URIs, or covert channels.
MCP05 — Privilege Escalation
? Not assessed0/7 mapped assessor rule(s) are proven to have executed; no adverse findings were observed, but the control is not assessed because execution evidence is incomplete. Unexecuted assessors: C2 (execution-ledger); C8 (execution-ledger); C10 (execution-ledger); C12 (execution-ledger); I4 (execution-ledger); I12 (execution-ledger); J1 (execution-ledger).
Control text:
Vertical privilege increases via JWT confusion, deserialization, evaluation of untrusted input, OAuth scope widening, or capability escalation post-initialization.
MCP06 — Excessive Permissions
? Not assessed0/7 mapped assessor rule(s) are proven to have executed; no adverse findings were observed, but the control is not assessed because execution evidence is incomplete. Unexecuted assessors: A2 (execution-ledger); B3 (execution-ledger); B7 (execution-ledger); E4 (execution-ledger); F2 (execution-ledger); I11 (execution-ledger); I16 (execution-ledger).
Control text:
Tools or roots claiming broader filesystem, network, or credential access than required for their stated function.
MCP07 — Insecure Configuration
? Not assessed0/11 mapped assessor rule(s) are proven to have executed; no adverse findings were observed, but the control is not assessed because execution evidence is incomplete. Unexecuted assessors: B6 (execution-ledger); C7 (execution-ledger); C8 (execution-ledger); C11 (execution-ledger); C14 (execution-ledger); C15 (execution-ledger); D6 (execution-ledger); E1 (execution-ledger); E2 (execution-ledger); I15 (execution-ledger); J4 (execution-ledger).
Control text:
Servers shipped with insecure defaults: no authentication, wildcard CORS, HTTP transport, weak session tokens, disabled TLS validation, empty sandboxes.
MCP08 — Dependency Vulnerabilities
? Not assessed0/7 mapped assessor rule(s) are proven to have executed; no adverse findings were observed, but the control is not assessed because execution evidence is incomplete. Unexecuted assessors: D1 (execution-ledger); D2 (execution-ledger); D3 (execution-ledger); D4 (execution-ledger); D5 (execution-ledger); D6 (execution-ledger); D7 (execution-ledger).
Control text:
Known-CVE, abandoned, malicious, or typosquatted dependencies shipped with the server.
MCP09 — Logging & Monitoring Failures
? Not assessed0/6 mapped assessor rule(s) are proven to have executed; no adverse findings were observed, but the control is not assessed because execution evidence is incomplete. Unexecuted assessors: C6 (execution-ledger); E3 (execution-ledger); K1 (execution-ledger); K2 (execution-ledger); K3 (execution-ledger); K20 (execution-ledger).
Control text:
Absent, insufficient, or tamperable audit logging that prevents incident detection and response.
MCP10 — Supply Chain Compromise
✗ Unmet0/27 mapped assessor rule(s) are proven to have executed; 1 finding(s) observed (1 critical); at least one finding is at or above the high threshold (status: unmet). 27 mapped assessor(s) did not execute, so this finding-backed result does not imply complete control coverage.
Control text:
Compromise of the build, publish, or distribution pipeline upstream of the server — including CI/CD token theft, build-artifact tampering, and manifest confusion.
- Critical Official Namespace Squatting (finding 2c2c43e6-03c7-4c7b-a6c8-318606fb49f7, confidence 90%) SOURCE: external-content at initialize.server_name — The MCP client surfaces the server name verbatim in its approval dialog, and the LLM ingests the server name alongside the tool descriptions. A nam
- If you own the server and are NOT affiliated with the vendor whose namespace it contains, rename the server to remove the vendor token. Choose a name that makes your actual publisher identity clear. If you ARE a vendor-approved partner and intentionally use the vendor's namespace, request inclusion in the rule's OFFICIAL_NAMESPACES.verified_github_orgs list by publishing the server under a vendor-sanctioned GitHub organisation. Users deciding whether to approve the server should check the repository owner against the vendor's published list of approved partners before granting trust.
Multi-step attack chains
No multi-step attack chains were synthesized for this server.
Cryptographic attestation
- Algorithm
- HMAC-SHA256
- Key ID
- mcps-hkdf-e8990a4e1526
- Signer
- mcp-sentinel/v1
- Signed at
- 2026-05-24T07:24:55.712Z
- Canonicalization
- RFC8785
HMAC-SHA256 signature (base64, wrapped at 64 chars):
GxFO0AffJrnia2JjGh+OsCCisgHJZtmnR5YlIJWOMok=
Verification instructions:
To verify this report: 1. Extract the report body (everything except the .attestation field). 2. Canonicalize the body via RFC 8785 (JCS). 3. Compute HMAC-SHA256 with the signing key for key_id "mcps-hkdf-e8990a4e1526". 4. Base64-encode the result and compare with the signature above.