Loading the registry…
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.
12 critical findings reported by cisco-skill-scanner, 1 of them in the installed artifact. The composite score alone does not reflect this — read the per-scanner reports below.
This artifact ships from 8 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. Some sources have no verdict at all; that is not a pass.
github: https://github.com/jmrplens/gitlab-mcp-server, 193 findings
Choose your runtime: the CLI writes the mcpServers config entry for that target.
nerlo install --target claude-code -- gitlab-mcp-server
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
21 findings · 2.4s
v2.0.11
109 findings · 276.5s
v0.3.26
Timed out
0 findings · 300.0s
v0.1.0
44 findings · 244.9s
v0.1.0
19 findings · 245.2s
v0.1.0
1 finding · 68.2s
No report in this scan: capslock, govulncheck, osv-scanner, trivy, trivy_image.
1 scan on record. Every scan's full results are retained immutably for 24 months.
| Completed | Composite | Change | Scanners | Status |
|---|---|---|---|---|
| Aug 2, 2026 | Scan Halted | — | agentshield: completecisco-skill-scanner: completeagent-audit-kit ·!: timeoutnerlo-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 194 findings across every scanner that examined this package. 11 of 12 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.
70 Documentation or example — The match is in documentation or sample code, confirmed by our own check to be outside the installed artifact.
Rules: YARA_coercive_injection_generic, opt.nerlo-rules.nerlo-install-fetch-raw-then-run, opt.nerlo-rules.nerlo-install-pipe-to-shell and 6 more · Files: /repo/docs/reference/tools/SKILL.md, /repo/docs/getting-started.md, /repo/site/src/content/docs/es/getting-started.mdx and 39 more · reported by cisco-skill-scanner, nerlo-install-instruction
18 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: COMMAND_INJECTION_EVAL, SQL_INJECTION_STRING_FORMAT, SECRET_AWS_KEY and 3 more · Files: /repo/test/fixtures/orbit/security-fixtures/src/acme/orders/auth.py, /repo/test/fixtures/orbit/security-fixtures/src/acme/orders/legacy_db.py, /repo/test/fixtures/orbit/security-fixtures/src/acme/orders/__init__.py and 5 more · reported by cisco-skill-scanner
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: MANIFEST_INVALID_NAME · Files: /repo/.github/agents/SKILL.md · reported by cisco-skill-scanner
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.
42 opt.nerlo-rules.nerlo-go-secret-to-network-egress
Files: /repo/cmd/audit_tokens/main.go, /repo/cmd/gen_llms/main.go, /repo/internal/tools/clusteragents/markdown.go and 12 more · reported by nerlo-behavioral
10 HIDDEN_DATA_FILE
Files: /repo/.gitguardian.yaml, /repo/.plugin/plugin.json, /repo/.markdownlint-cli2.jsonc and 7 more · reported by cisco-skill-scanner
6 FILE_MAGIC_MISMATCH
Files: /repo/llms-full-meta-tools.txt, /repo/llms-full.txt, /repo/llms.txt and 3 more · reported by cisco-skill-scanner
4 MANIFEST_MISSING_LICENSE
Files: /repo/SKILL.md, /repo/site/src/content/i18n/SKILL.md, /repo/cmd/eval_mcp_surfaces/SKILL.md and 1 more · reported by cisco-skill-scanner
4 opt.nerlo-rules.nerlo-install-fetch-raw-then-run
Files: /repo/README.md, /repo/scripts/install.ps1, /repo/scripts/install.sh · reported by nerlo-install-instruction
The model could have called any of these a false positive and did not.
1 OVERSIZED_FILE
Files: /repo/internal/tools/testdata/tools_individual.json · reported by cisco-skill-scanner
Critical prompt injection and credential network egress risks identified.
The artifact contains a critical prompt injection vulnerability in `user_crud.go`, which could allow manipulation of AI model interactions. Additionally, it can access credentials and transmit them over the network from `audit_tokens/main.go` and `gen_llms/main.go`. Several agent configurations also lack tool restrictions or have comment injection issues, potentially leading to unintended actions.
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.
3 SOCIAL_ENG_VAGUE_DESCRIPTION
Files: /repo/SKILL.md, /repo/site/src/content/i18n/SKILL.md, /repo/cmd/eval_mcp_surfaces/SKILL.md · reported by cisco-skill-scanner
2 DATA_EXFIL_JS_NETWORK
Files: /repo/site/astro.config.mjs, /repo/site/scripts/sync-identity.mjs · reported by cisco-skill-scanner
2 MANIFEST_INVALID_NAME
Files: /repo/.claude/agents/SKILL.md, /repo/cmd/eval_mcp_surfaces/SKILL.md · reported by cisco-skill-scanner
2 opt.nerlo-rules.nerlo-hardcoded-external-egress
Files: /repo/site/astro.config.mjs, /repo/site/scripts/sync-identity.mjs · reported by nerlo-behavioral
2 opt.nerlo-rules.nerlo-install-pipe-to-shell
Files: /repo/README.md, /repo/scripts/install.sh · reported by nerlo-install-instruction
2 PIPELINE_TAINT_FLOW
Files: /repo/README.md, /repo/SKILL.md · reported by cisco-skill-scanner
1 agents-comment-injection-3546
Files: agents/documentation-writer.agent.md · reported by agentshield
1 agents-no-model-agents/debug.agent.md
Files: agents/debug.agent.md · reported by agentshield
1 agents-no-model-agents/documentation-writer.agent.md
Files: agents/documentation-writer.agent.md · reported by agentshield
1 agents-no-model-agents/go-mcp-expert.agent.md
Files: agents/go-mcp-expert.agent.md · reported by agentshield
1 agents-no-model-agents/go-source-documenter.agent.md
Files: agents/go-source-documenter.agent.md · reported by agentshield
1 agents-no-model-agents/plan-expert.agent.md
Files: agents/plan-expert.agent.md · reported by agentshield
1 agents-no-model-agents/se-reviewer.agent.md
Files: agents/se-reviewer.agent.md · reported by agentshield
1 agents-no-model-agents/test-expert.agent.md
Files: agents/test-expert.agent.md · reported by agentshield
1 agents-no-tools-agents/debug.agent.md
Files: agents/debug.agent.md · reported by agentshield
1 agents-no-tools-agents/documentation-writer.agent.md
Files: agents/documentation-writer.agent.md · reported by agentshield
1 agents-no-tools-agents/go-mcp-expert.agent.md
Files: agents/go-mcp-expert.agent.md · reported by agentshield
1 agents-no-tools-agents/go-source-documenter.agent.md
Files: agents/go-source-documenter.agent.md · reported by agentshield
1 agents-no-tools-agents/plan-expert.agent.md
Files: agents/plan-expert.agent.md · reported by agentshield
1 agents-no-tools-agents/se-reviewer.agent.md
Files: agents/se-reviewer.agent.md · reported by agentshield
1 agents-no-tools-agents/test-expert.agent.md
Files: agents/test-expert.agent.md · reported by agentshield
1 agents-oversized-prompt-agents/documentation-writer.agent.md
Files: agents/documentation-writer.agent.md · reported by agentshield
1 agents-oversized-prompt-agents/go-mcp-expert.agent.md
Files: agents/go-mcp-expert.agent.md · reported by agentshield
1 agents-oversized-prompt-agents/go-source-documenter.agent.md
Files: agents/go-source-documenter.agent.md · reported by agentshield
1 agents-oversized-prompt-agents/plan-expert.agent.md
Files: agents/plan-expert.agent.md · reported by agentshield
1 agents-oversized-prompt-agents/se-reviewer.agent.md
Files: agents/se-reviewer.agent.md · reported by agentshield
1 agents-oversized-prompt-agents/test-expert.agent.md
Files: agents/test-expert.agent.md · reported by agentshield
1 EXCESSIVE_FILE_COUNT
Files: /repo/. · reported by cisco-skill-scanner
1 nerlo-malware-obfuscated_blob
Files: github_release:checksums.txt.sigstore.json · reported by nerlo-malware
1 opt.nerlo-rules.nerlo-install-run-bundled-artifact
Files: /repo/scripts/install.ps1 · reported by nerlo-install-instruction
1 YARA_prompt_injection_generic
Files: /repo/internal/tools/users/user_crud.go · reported by cisco-skill-scanner
Showing 25 of 57; the rest are in the per-scanner reports above.