Loading the registry…
Working-memory shelf for AI agents — offload closed topics to a docshelf shelf as digest-indexed episodes, recall by index.
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.
2 critical findings reported by agent-audit-kit, 1 of them in the installed artifact. The composite score alone does not reflect this — read the per-scanner reports below.
github: https://github.com/ignatenkofi/memshelf-mcp, 34 findings
Choose your runtime: the CLI writes the mcpServers config entry for that target.
nerlo install --target claude-code -- memshelf-mcp
Install respects the composite badge: Clean proceeds, Caution prompts for confirmation, and Flagged is refused. Write operations require an API token.
4 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
20 findings · 12.2s
v0.3.26
9 findings · 4.4s
v0.1.0
0 findings · 28.4s
v0.1.0
1 finding · 28.4s
v1.4.0
This scanner found nothing in this artifact that it assesses. What each scanner covers
0 findings · 0.3s
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, nerlo-multi-source.
1 scan on record. Every scan's full results are retained immutably for 24 months.
| Completed | Composite | Change | Scanners | Status |
|---|---|---|---|---|
| Aug 7, 2026 | Scan Halted | — | agentshield ·n/a: not applicablecisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completecapslock ·n/a: not applicable | 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 30 findings across every scanner that examined this package. 1 of 2 findings rated critical by their scanner was among the dismissals.
Not reviewed is not the same as clean. Those 4 findings 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.
7 Documentation or example — The match is in documentation or sample code, confirmed by our own check to be outside the installed artifact.
Rules: AAK-HEALTHCARE-AI-004, SOCIAL_ENG_VAGUE_DESCRIPTION, MANIFEST_INVALID_NAME · Files: docs/DECISIONS.md, /repo/.github/SKILL.md, /repo/docs/SKILL.md and 2 more · reported by agent-audit-kit, cisco-skill-scanner
2 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/security.yml, .github/workflows/release.yml · reported by agent-audit-kit
2 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-MCP-STDIO-CMD-INJ-001, AAK-ANTHROPIC-SDK-001 · Files: tests/test_stdio_protocol.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.
4 MANIFEST_MISSING_LICENSE
Files: /repo/adapters/claude-code/skills/shelve/SKILL.md, /repo/SKILL.md, /repo/adapters/claude-code/SKILL.md and 1 more · reported by cisco-skill-scanner
3 SOCIAL_ENG_VAGUE_DESCRIPTION
Files: /repo/SKILL.md, /repo/adapters/claude-code/SKILL.md, /repo/adapters/shelf-repo/SKILL.md · reported by cisco-skill-scanner
2 DATA_EXFIL_NETWORK_REQUESTS
Files: /repo/src/memshelf_mcp/core/remote.py · reported by cisco-skill-scanner
1 AAK-OAUTH-3P-001
Files: pyproject.toml · reported by agent-audit-kit
1 AAK-SSRF-001
Files: src/memshelf_mcp/server.py · reported by agent-audit-kit
1 AAK-SSRF-005
Files:
4 The model did not answer for these findings.
Rules: MANIFEST_MISSING_LICENSE · Files: /repo/.github/SKILL.md, /repo/docs/SKILL.md, /repo/.github/ISSUE_TEMPLATE/SKILL.md and 1 more · reported by cisco-skill-scanner
Artifact has critical SSRF vulnerabilities and network egress capabilities.
The artifact contains a critical Server-Side Request Forgery (SSRF) vulnerability in `src/memshelf_mcp/server.py`, which could allow requests to arbitrary network resources. It also exhibits high-severity SSRF in the same file and undeclared network egress. Additionally, the artifact can run bundled artifacts and may access third-party OAuth credentials.
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.
1 AAK-SUPPLY-004
Files: pyproject.toml · reported by agent-audit-kit
1 opt.nerlo-rules.nerlo-install-run-bundled-artifact
Files: /repo/adapters/claude-code/README.md · reported by nerlo-install-instruction
1 TOOL_ABUSE_UNDECLARED_NETWORK
Files: /repo/repo/CHANGELOG.md · reported by cisco-skill-scanner