Pseudolife persistent long-term memory for MCP-compatible coding agents
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.
7 critical findings reported by agent-audit-kit, 2 of them in the installed artifact. 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/Pseudogiant-xr/Pseudolife-MCP, 363 findings
Choose your runtime: the CLI writes the mcpServers config entry for that target.
nerlo install --target claude-code -- pseudolife-mcp
Install respects the composite badge: Clean proceeds, Caution prompts for confirmation, and Flagged is refused. Write operations require an API token.
6 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.
v1.4.0
0 findings · 0.4s
v2.0.11
Timed out
0 findings · 300.0s
v0.3.74
84 findings · 104.6s
v0.2.0
15 findings · 24.5s
v0.2.0
264 findings · 24.5s
v0.1.0
0 findings · 33.2s
vv0.3.2
No Go packages were found in this artifact. What each scanner covers
0 findings · 0.1s
No report in this scan: govulncheck, osv-scanner, trivy, trivy_image.
4 scans on record. Every scan's full results are retained immutably for 24 months.
| Completed | Composite | Change | Scanners | Status |
|---|---|---|---|---|
| Sep 26, 2026 | Scan Halted | — | agentshield: completecisco-skill-scanner ·!: timeoutagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completecapslock ·n/a: not applicablenerlo-multi-source: complete | rejected |
| Aug 3, 2026 | Scan Halted | — | agentshield: completecisco-skill-scanner ·!: incompleteagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completenerlo-multi-source: complete | rejected |
| Jul 31, 2026 | Scan Halted | — | agentshield: completecisco-skill-scanner ·!: timeoutagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completenerlo-multi-source: complete | rejected |
| Jul 29, 2026 | Flagged25 | — | agentshield: completecisco-skill-scanner ·!: timeoutagent-audit-kit ·!: timeoutnerlo-behavioral: completenerlo-install-instruction: completenerlo-multi-source: completetrivy ·n/a: not applicableosv-scanner: completetrivy_image ·n/a: not applicable | completed |
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 363 findings across every scanner that examined this package. 5 of 7 findings rated critical by their scanner were among the dismissals.
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.
242 Documentation or example — The match is in documentation or sample code, confirmed by our own check to be outside the installed artifact.
Rules: opt.nerlo-rules.nerlo-install-zero-width-in-text, AAK-HEALTHCARE-AI-004, AAK-MCP-ATTEST-001 and 3 more · Files: /repo/docs/specs/2026-06-26-session-briefing-plan.md, docs/guide/memory-model.md, docs/superpowers/specs/2026-06-28-relation-extraction-eval-design.md and 43 more · reported by nerlo-install-instruction, agent-audit-kit
29 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-INDIA-PII-001, AAK-MCP-MARKETPLACE-CONFIG-FETCH-001, AAK-STDIO-001 and 7 more · Files: tests/test_coordination_turn_digest.py, tests/test_coordination_roster_hygiene.py, tests/test_shim.py and 18 more · reported by agent-audit-kit
4 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/release.yml · reported by agent-audit-kit
1 Agent instruction file — The match is in a file that instructs an AI coding agent — a CLAUDE.md or similar. It is documentation of intent, and our own check confirmed it is not part of what gets installed.
Rules: AAK-AGENT-003 · Files: CLAUDE.md · 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.
23 opt.nerlo-rules.nerlo-install-run-bundled-artifact
Files: /repo/CHANGELOG.md, /repo/evals/README.md, /repo/llms-full.txt and 7 more · reported by nerlo-install-instruction
21 AAK-SECRET-004
Files: pseudolife_memory/credentials.py, pseudolife_memory/daemon.py, pseudolife_memory/coordination_identity.py and 15 more · reported by agent-audit-kit
14 opt.nerlo-rules.nerlo-py-secret-to-network-egress
Files: /repo/evals/answerability_probe.py, /repo/evals/classify_entity_kinds.py, /repo/evals/cognee_adapter.py and 10 more · reported by nerlo-behavioral
5 AAK-IPI-WILD-CORPUS-001
Files: CHANGELOG.md, evals/epistemic_bench.py, evals/coordination_audit_volume.py and 2 more · reported by agent-audit-kit
4 AAK-MCP-018
Files: pseudolife_memory/mcp_server.py, pseudolife_memory/daemon.py, evals/memory_policy_daemon.py and 1 more · reported by agent-audit-kit
Critical path traversal and direct I/O access
The artifact contains a critical path traversal vulnerability in `pseudolife_memory/coordination_identity.py`, which could allow unauthorized file system access. Direct standard I/O access is present in `pseudolife_memory/doctor_cli.py`, enabling potential arbitrary command execution. Additionally, multiple high-severity findings indicate potential credential access and network egress capabilities across various files, including `evals/capture_metrics.py` and `pseudolife_memory/credentials.py`.
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.
4 AAK-SSRF-002
Files: pseudolife_memory/mcp_server.py, evals/memory_policy_daemon.py, pseudolife_memory/web/devserver.py and 1 more · reported by agent-audit-kit
3 AAK-HEALTHCARE-AI-004
Files: llms-full.txt, README.md, evals/README.md · reported by agent-audit-kit
3 opt.nerlo-rules.nerlo-install-shell-inline-command
Files: /repo/CHANGELOG.md, /repo/evals/README.md · reported by nerlo-install-instruction
2 AAK-MCP-SSRF-001
Files: pseudolife_memory/shim.py, evals/taubench_adapter.py · reported by agent-audit-kit
2 AAK-SPLUNK-TOKLOG-001
Files: pseudolife_memory/coordination_adapter.py, pseudolife_memory/shim.py · reported by agent-audit-kit
1 AAK-MARKETPLACE-001
Files: .claude-plugin/marketplace.json · reported by agent-audit-kit
1 AAK-MCP-AUTH-PATHTRAVERSAL-001
Files: pseudolife_memory/coordination_identity.py · reported by agent-audit-kit
1 AAK-OAUTH-3P-001
Files: pyproject.toml · reported by agent-audit-kit
1 AAK-STDIO-001
Files: pseudolife_memory/doctor_cli.py · reported by agent-audit-kit
1 AAK-SUPPLY-004
Files: pyproject.toml · reported by agent-audit-kit
1 opt.nerlo-rules.nerlo-js-secret-to-network-egress
Files: /repo/pseudolife_memory/web/static/js/api.js · reported by nerlo-behavioral
Showing 25 of 50; the rest are in the per-scanner reports above.