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.
207 critical findings reported by cisco-skill-scanner, agent-audit-kit, 97 of them in the installed artifact. The composite score alone does not reflect this — read the per-scanner reports below.
This artifact ships from 3 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/lacs-project/sysknife, 505 findings
Choose your runtime: the CLI writes the mcpServers config entry for that target.
nerlo install --target claude-code -- sysknife
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 · 1.4s
v2.0.11
326 findings · 42.3s
v0.3.26
157 findings · 26.1s
v0.1.0
0 findings · 37.8s
v0.1.0
22 findings · 37.9s
v0.1.0
0 findings · 27.7s
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: 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 505 findings across every scanner that examined this package. 110 of 207 findings rated critical by their scanner were among the dismissals.
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.
119 Documentation or example — The match is in documentation or sample code, confirmed by our own check to be outside the installed artifact.
Rules: YARA_credential_harvesting_generic, YARA_command_injection_generic, COMPOUND_FIND_EXEC and 8 more · Files: /repo/docs/security/red-team-2026-04-26.md, /repo/docs/security/SKILL.md, /repo/tests/e2e/stories/story-91.sh and 19 more · reported by cisco-skill-scanner, nerlo-install-instruction, agent-audit-kit
70 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: TOOL_ABUSE_SYSTEM_MODIFICATION, COMMAND_INJECTION_JS_CHILD_PROCESS, AAK-SECRET-004 and 2 more · Files: /repo/tests/e2e/atomic-vm.sh, /repo/tests/e2e/exec/exec-5.sh, /repo/tests/e2e/exec/run-exec-stories.sh and 16 more · reported by cisco-skill-scanner, agent-audit-kit
59 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-001 · Files: CLAUDE.md · reported by agent-audit-kit
1 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: MANIFEST_INVALID_NAME · Files: /repo/.github/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.
61 AAK-TAINT-002
Files: apps/sysknife-cli/src/runner.rs, crates/sysknife-daemon/src/dispatcher.rs, crates/sysknife-daemon/src/executor.rs and 3 more · reported by agent-audit-kit
43 YARA_system_manipulation_generic
Files: /repo/crates/sysknife-daemon-test/src/main.rs, /repo/crates/sysknife-daemon/src/actions/containers.rs, /repo/crates/sysknife-daemon/src/actions/flatpak.rs and 4 more · reported by cisco-skill-scanner
28 DATA_EXFIL_JS_FS_ACCESS
Files: /repo/packages/setup/index.js, /repo/packages/setup/install-binary.js, /repo/packages/setup/mcp-config.js · reported by cisco-skill-scanner
24 AAK-SECRET-004
Files: apps/sysknife-cli/src/mcp_server.rs, crates/sysknife-daemon/src/main.rs, crates/sysknife-daemon/src/transactions.rs and 3 more · reported by agent-audit-kit
21 YARA_command_injection_generic
Files: /repo/crates/sysknife-daemon/src/actions/fail2ban.rs, /repo/crates/sysknife-daemon/src/actions/snap.rs, /repo/crates/sysknife-daemon/src/actions/validate.rs and 1 more
The model could have called any of these a false positive and did not.
10 YARA_prompt_injection_unicode_steganography
Files: /repo/assets/demo/mcp-flow.gif · reported by cisco-skill-scanner
1 The model called these false positives and our own check did not agree, so the dismissal was refused.
Rules: HIDDEN_DATA_FILE · Files: /repo/.mcp.json.example · reported by cisco-skill-scanner
Artifact has critical command injection and secret exposure risks.
The artifact contains multiple critical command injection vulnerabilities, including in JavaScript child processes, which could lead to shell execution. It also exposes a critical secret. Additionally, the artifact has high-severity findings related to system manipulation and further secret exposures.
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.
14 COMMAND_INJECTION_JS_CHILD_PROCESS
Files: /repo/packages/setup/index.js, /repo/packages/setup/install-daemon.js, /repo/packages/setup/mcp-launcher.js · reported by cisco-skill-scanner
8 MANIFEST_MISSING_LICENSE
Files: /repo/SKILL.md, /repo/.codex-plugin/SKILL.md, /repo/.claude/SKILL.md and 5 more · reported by cisco-skill-scanner
8 SOCIAL_ENG_VAGUE_DESCRIPTION
Files: /repo/SKILL.md, /repo/.codex-plugin/SKILL.md, /repo/.claude/SKILL.md and 5 more · reported by cisco-skill-scanner
7 HIDDEN_DATA_FILE
Files: /repo/.markdown-link-check.json, /repo/.codex-plugin/mcp.json, /repo/.pre-commit-config.yaml and 4 more · reported by cisco-skill-scanner
7 opt.nerlo-rules.nerlo-install-run-bundled-artifact
Files: /repo/CONTRIBUTING.md, /repo/HACKING.md · reported by nerlo-install-instruction
6 DATA_EXFIL_JS_NETWORK
Files: /repo/packages/setup/install-binary.js · reported by cisco-skill-scanner
4 PIPELINE_TAINT_FLOW
Files: /repo/HACKING.md, /repo/SKILL.md · reported by cisco-skill-scanner
3 YARA_code_execution_generic
Files: /repo/packaging/sysknife-mount-edit, /repo/packaging/sysknife-scheduled-job-edit, /repo/packaging/sysknife-sysctl-edit · reported by cisco-skill-scanner
2 opt.nerlo-rules.nerlo-install-pipe-to-shell
Files: /repo/HACKING.md, /repo/packages/setup/node-preflight.js · reported by nerlo-install-instruction
1 AAK-HEALTHCARE-AI-005
Files: CHANGELOG.md · reported by agent-audit-kit
1 AAK-LEGAL-002
Files: apps/sysknife-shell/package.json · reported by agent-audit-kit
1 AAK-MCP-006
Files: .codex-plugin/mcp.json · reported by agent-audit-kit
1 AAK-SECRET-003
Files: crates/sysknife-brain/src/prefs.rs · reported by agent-audit-kit
1 AAK-SUPPLY-005
Files: Cargo.lock · reported by agent-audit-kit
1 EXCESSIVE_FILE_COUNT
Files: /repo/. · reported by cisco-skill-scanner
1 LOW_ANALYZABILITY
Files: /repo/packages/setup · reported by cisco-skill-scanner
1 MANIFEST_INVALID_NAME
Files: /repo/.codex-plugin/SKILL.md · reported by cisco-skill-scanner
1 TOOL_ABUSE_SYSTEM_PACKAGE_INSTALL
Files: /repo/scripts/ci-local.sh · reported by cisco-skill-scanner
Showing 25 of 168; the rest are in the per-scanner reports above.