Loading the registry…
Interactively investigate compiler output
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.
44 critical findings reported by cisco-skill-scanner, 42 of them in the installed artifact. The composite score alone does not reflect this — read the per-scanner reports below.
Choose your runtime: the CLI writes the mcpServers config entry for that target.
nerlo install --target claude-code -- compiler-explorer
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
34 findings · 1.0s
v2.0.11
252 findings · 55.3s
v0.3.74
Timed out
0 findings · 450.0s
v0.1.0
4 findings · 23.1s
v0.1.0
12 findings · 23.2s
vv0.3.2
Incomplete run
0 findings · 0.4s
v0.1.0
This scanner found nothing in this artifact that it assesses. What each scanner covers
0 findings · 1.9s
No report in this scan: 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 20, 2026 | Scan Halted | — | agentshield: completecisco-skill-scanner: completeagent-audit-kit ·!: timeoutnerlo-behavioral: completenerlo-install-instruction: completecapslock ·!: incompletenerlo-multi-source ·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 302 findings across every scanner that examined this package. 2 of 44 findings rated critical by their scanner were among the dismissals.
Not reviewed is not the same as clean. Those 22 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.
23 Documentation or example — The match is in documentation or sample code, confirmed by our own check to be outside the installed artifact.
Rules: RESOURCE_ABUSE_INFINITE_LOOP, opt.nerlo-rules.nerlo-install-fetch-raw-then-run, opt.nerlo-rules.nerlo-install-pipe-to-shell and 6 more · Files: /repo/examples/numba/generator.py, /repo/docs/WindowsSubsystemForLinux.md, /repo/docs/SKILL.md and 9 more · reported by cisco-skill-scanner, nerlo-install-instruction
10 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, FILE_MAGIC_MISMATCH, OVERSIZED_FILE and 2 more · Files: /repo/test/demangler-tests.ts, /repo/test/mcp/mcp-tests.ts, /repo/test/filters-cases/bug-5020.asm.directives.labels.comments.library.json and 6 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: TOOL_ABUSE_UNDECLARED_NETWORK · Files: /repo/repo/AGENTS.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.
113 DATA_EXFIL_JS_FS_ACCESS
Files: /repo/etc/scripts/docenizers/docenizer-java.ts, /repo/lib/app/compiler-discovery.ts, /repo/lib/app/main.ts and 50 more · reported by cisco-skill-scanner
24 COMMAND_INJECTION_EVAL
Files: /repo/etc/scripts/ast_dump.py, /repo/etc/scripts/disasms/dis_all.py, /repo/lib/base-compiler.ts and 16 more · reported by cisco-skill-scanner
21 DATA_EXFIL_JS_NETWORK
Files: /repo/lib/buildenvsetup/ceconan.ts, /repo/lib/execution/execution-query.ts, /repo/lib/mcp/tools/compile.ts and 12 more · reported by cisco-skill-scanner
19 FILE_MAGIC_MISMATCH
Files: /repo/static/modes/nc-mode.ts, /repo/static/modes/ispc-mode.ts, /repo/static/panes/ast-view.ts and 16 more · reported by cisco-skill-scanner
13 COMMAND_INJECTION_JS_CHILD_PROCESS
Files: /repo/lib/app/cli.ts, /repo/lib/app/temp-dir.ts, /repo/lib/compilation-env.ts and 4 more · reported by cisco-skill-scanner
22 The model called these false positives and our own check did not agree, so the dismissal was refused.
Rules: skills-missing-governance-.claude/commands/hunt-sentry-issues.md, skills-missing-governance-.claude/commands/hunt-github-issues.md, skills-missing-governance-commands/hunt-sentry-issues.md and 18 more · Files: .claude/commands/hunt-sentry-issues.md, .claude/commands/hunt-github-issues.md, commands/hunt-sentry-issues.md and 7 more · reported by agentshield
Artifact contains critical command injection and credential harvesting risks.
The artifact exhibits critical command injection vulnerabilities in multiple scripts and compiler components, allowing for shell execution. It also contains critical path traversal vulnerabilities in docenizer scripts and critical credential harvesting patterns in NSJail configuration files. Additionally, high severity findings indicate potential network egress of secrets and dynamic code execution.
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.
8 DATA_EXFIL_NETWORK_REQUESTS
Files: /repo/etc/scripts/check_infra_settings.py, /repo/etc/scripts/docenizers/docenizer-6502.py, /repo/etc/scripts/docenizers/docenizer-avr.py and 4 more · reported by cisco-skill-scanner
8 MANIFEST_MISSING_LICENSE
Files: /repo/SKILL.md, /repo/cypress/SKILL.md, /repo/.claude/agents/SKILL.md and 5 more · reported by cisco-skill-scanner
7 SOCIAL_ENG_VAGUE_DESCRIPTION
Files: /repo/SKILL.md, /repo/cypress/SKILL.md, /repo/.claude/commands/SKILL.md and 4 more · reported by cisco-skill-scanner
4 opt.nerlo-rules.nerlo-install-run-bundled-artifact
Files: /repo/etc/scripts/ce-properties-wizard/README.md · reported by nerlo-install-instruction
3 PATH_TRAVERSAL_OPEN
Files: /repo/etc/scripts/docenizers/docenizer-amd64.py, /repo/etc/scripts/docenizers/docenizer-arm.py, /repo/etc/scripts/docenizers/docenizer-evm.py · reported by cisco-skill-scanner
2 agents-encoded-payload-6930
Files: agents/compiler-explorer-architect.md, .claude/agents/compiler-explorer-architect.md · reported by agentshield
2 HIDDEN_DATA_FILE
Files: /repo/.minimum-node-version, /repo/.git-blame-ignore-revs · reported by cisco-skill-scanner
2 LOW_ANALYZABILITY
Files: /repo/cypress, /repo · reported by cisco-skill-scanner
2 opt.nerlo-rules.nerlo-dynamic-exec
Files: /repo/etc/webpack/parsed-pug-loader.js, /repo/lib/exec.ts · reported by nerlo-behavioral
2 opt.nerlo-rules.nerlo-py-secret-to-network-egress
Files: /repo/etc/scripts/util/contributorer.py, /repo/etc/scripts/util/formatcheck.py · reported by nerlo-behavioral
2 YARA_credential_harvesting_generic
Files: /repo/etc/nsjail/compilers-and-tools.cfg, /repo/etc/nsjail/user-execution.cfg · reported by cisco-skill-scanner
1 agents-no-model-.claude/agents/compiler-config.md
Files: .claude/agents/compiler-config.md · reported by agentshield
1 agents-no-model-.claude/agents/compiler-explorer-architect.md
Files: .claude/agents/compiler-explorer-architect.md · reported by agentshield
1 agents-no-model-agents/compiler-config.md
Files: agents/compiler-config.md · reported by agentshield
1 agents-no-model-agents/compiler-explorer-architect.md
Files: agents/compiler-explorer-architect.md · reported by agentshield
1 agents-no-tools-.claude/agents/compiler-config.md
Files: .claude/agents/compiler-config.md · reported by agentshield
1 agents-no-tools-.claude/agents/compiler-explorer-architect.md
Files: .claude/agents/compiler-explorer-architect.md · reported by agentshield
1 agents-no-tools-agents/compiler-config.md
Files: agents/compiler-config.md · reported by agentshield
1 agents-no-tools-agents/compiler-explorer-architect.md
Files: agents/compiler-explorer-architect.md · reported by agentshield
1 agents-oversized-prompt-.claude/agents/compiler-explorer-architect.md
Files: .claude/agents/compiler-explorer-architect.md · reported by agentshield
1 agents-oversized-prompt-agents/compiler-explorer-architect.md
Files: agents/compiler-explorer-architect.md · reported by agentshield
1 EXCESSIVE_FILE_COUNT
Files: /repo/. · reported by cisco-skill-scanner
1 MANIFEST_INVALID_NAME
Files: /repo/etc/scripts/gh_tool/SKILL.md · reported by cisco-skill-scanner
1 OBFUSCATION_XOR_ENCODING
Files: /repo/static/utils.ts · reported by cisco-skill-scanner
1 YARA_prompt_injection_unicode_steganography
Files: /repo/public/template_screenshots/Rust-Cargo-IDE.default.png · reported by cisco-skill-scanner
Showing 25 of 52; the rest are in the per-scanner reports above.