CPersona — Persistent AI memory server with 3-layer hybrid search, confidence scoring, and 29 tools. MIT licensed.
The publisher performed an authenticated act of publication — proving control of a namespace in the official MCP registry, or appearing in a first-party catalogue an operator curates. That establishes WHO published it. It is not a security finding, and attested artifacts carry Flagged verdicts too.
1 critical finding reported by agent-audit-kit. The composite score alone does not reflect this — read the per-scanner reports below.
This artifact ships from 2 sources and their verdicts differ. The worst is github (Flagged). Installing from a cleaner source does not mean the others are safe — check the source you actually install from.
github: https://github.com/Cloto-dev/cpersona, 38 findings
Choose your runtime: the CLI writes the mcpServers config entry for that target.
nerlo install --target claude-code -- cpersona
Install respects the composite badge: Clean proceeds, Caution prompts for confirmation, and Flagged is refused. Write operations require an API token.
5 of 11 scanners examined this package. The rest do not apply to it — language, ecosystem and packaging decide which analyzers can say anything, and a scanner that cannot examine an artifact reports nothing rather than passing it.
v2.0.11
Timed out
0 findings · 300.0s
v0.3.26
22 findings · 95.3s
v0.1.0
0 findings · 71.9s
v0.1.0
1 finding · 71.9s
v0.1.0
0 findings · 33.2s
v1.4.0
This scanner found nothing in this artifact that it assesses. What each scanner covers
0 findings · 1.5s
No report in this scan: capslock, govulncheck, osv-scanner, trivy, trivy_image.
3 scans on record. Every scan's full results are retained immutably for 24 months.
| Completed | Composite | Change | Scanners | Status |
|---|---|---|---|---|
| Aug 3, 2026 | Scan Halted | — | agentshield ·n/a: not applicablecisco-skill-scanner ·!: timeoutagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completenerlo-multi-source: complete | rejected |
| Jul 30, 2026 | Scan Halted | — | cisco-skill-scanner ·!: timeoutagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completenerlo-multi-source: complete | rejected |
| Jul 29, 2026 | Scan Halted | — | cisco-skill-scanner ·!: timeoutagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completenerlo-multi-source: complete | rejected |
Findings in files this artifact installs stand as reported; a model re-read the rest and said which ones it believes are false positives. This is a second opinion published beside the evidence, not a correction to it: the per-scanner reports above are unchanged, every dismissed finding is still listed there at its original severity, and the score and the Flagged badge are computed from those raw severities alone. Nothing below moved them.
Out of 23 findings across every scanner that examined this package. None of the 1 finding rated critical by their scanner were dismissed.
Not reviewed is not the same as clean. Those 1 finding stand exactly as their scanners reported them, at full severity, as they would have without this review.
Two keys had to turn. The model had to name a reason from a fixed list of six, and a deterministic check of ours — over which files this artifact actually installs — had to independently agree. Anything it could not corroborate is in “not reviewed” above, at full severity.
3 CI or editor configuration — The match is in build, CI or editor configuration, confirmed by our own check to be outside the installed artifact.
Rules: AAK-GHA-IMMUTABLE-001 · Files: .github/workflows/ci.yml, .github/workflows/publish.yml · reported by agent-audit-kit
1 Test or fixture file — The match is in a test or fixture. Our own check confirmed the file is not part of what gets installed.
Rules: AAK-ANTHROPIC-SDK-001 · Files: tests/test_253_followups.py · reported by agent-audit-kit
These findings are in files this artifact installs and are not placeholder values. No false-positive basis can be corroborated for such a finding, so this review never dismisses one; they were not sent to the model and stand at their scanner's severity.
5 AAK-SECRET-004
Files: cpersona/proxy_stdio.py, cpersona/server.py, cpersona/memory_handlers.py and 2 more · reported by agent-audit-kit
4 AAK-ANTHROPIC-SDK-001
Files: cpersona/server.py, cpersona/_vendored_mcp_common/llm_provider.py, cpersona/_vendored_mcp_common/mcp_stream_interceptor.py and 1 more · reported by agent-audit-kit
2 AAK-HEALTHCARE-AI-004
Files: SUPPORT.md, qa/issue-registry.json · reported by agent-audit-kit
2 AAK-MCP-STATELESS-001
Files: cpersona/proxy_stdio.py, cpersona/server.py · reported by agent-audit-kit
1 AAK-DNS-REBIND-001
Files: cpersona/server.py · reported by agent-audit-kit
1 AAK-IPI-WILD-CORPUS-001
Files: cpersona/database.py · reported by agent-audit-kit
1 AAK-OAUTH-3P-001
Files: pyproject.toml · reported by agent-audit-kit
1 AAK-TASKS-003
Files: cpersona/tasks.py · reported by agent-audit-kit
1 opt.nerlo-rules.nerlo-install-run-bundled-artifact
Files: /repo/benchmarks/measurements/README.md · reported by nerlo-install-instruction
1 The model did not answer for these findings.
Rules: AAK-TASKS-003 · Files: tests/test_task_queue.py · reported by agent-audit-kit
Critical DNS rebinding and credential access risks identified.
The artifact exhibits critical DNS rebinding behavior in `cpersona/server.py`, which could facilitate network egress to unintended destinations. Multiple high-severity findings indicate potential credential access in `cpersona/config.py`, `cpersona/memory_handlers.py`, `cpersona/proxy_stdio.py`, and `cpersona/server.py`. Additionally, the artifact uses the Anthropic SDK in several files, including `cpersona/_vendored_mcp_common/llm_provider.py`, and interacts with a database in `cpersona/database.py` with a high-severity finding related to data handling.
Concern level assessed by the review: Critical. This is the review's scale, not the registry badge.
Reviewed by gemini-2.5-flash. The model sees the findings, not your code, and cannot change a score.