Loading the registry…
We found this by crawling public sources and nobody has attested to it. That is how most of the registry gets here, and it is not a mark against the artifact — it only means no authenticated act of publication is on record. An artifact can be the vendor's own and still appear here.
660 critical findings reported by cisco-skill-scanner, agent-audit-kit, 657 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 -- liter-llm
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 · 0.8s
v2.0.11
1236 findings · 103.7s
v0.3.74
789 findings · 57.3s
v0.1.0
2 findings · 14.5s
v0.1.0
3 findings · 14.7s
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 · 1.8s
No report in this scan: govulncheck, osv-scanner, trivy, trivy_image.
2 scans on record. Every scan's full results are retained immutably for 24 months.
| Completed | Composite | Change | Scanners | Status |
|---|---|---|---|---|
| Sep 3, 2026 | Scan Halted | — | agentshield: completecisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completecapslock ·!: incompletenerlo-multi-source ·n/a: not applicable | rejected |
| Aug 12, 2026 | Scan Halted | — | agentshield: completecisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completecapslock ·!: incomplete | 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 2,030 findings across every scanner that examined this package. 3 of 660 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.
93 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, HIDDEN_DATA_FILE · Files: .github/workflows/ci-rust.yaml, .github/workflows/ci-lint.yaml, .github/workflows/validate-pr.yml and 12 more · reported by agent-audit-kit, cisco-skill-scanner
40 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-005, PIPELINE_TAINT_FLOW, opt.nerlo-rules.nerlo-install-pipe-to-shell and 4 more · Files: docs-site/src/content/docs/reference/api-swift.md, docs-site/src/content/docs/reference/api-elixir.md, docs-site/src/content/docs/reference/api-java.md and 26 more · reported by agent-audit-kit, cisco-skill-scanner, nerlo-install-instruction
37 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_JS_CHILD_PROCESS, AAK-SECRET-001, AAK-SECRET-004 and 6 more · Files: /repo/e2e/node/globalSetup.ts, /repo/e2e/wasm/globalSetup.ts, crates/liter-llm/tests/live_providers/anthropic.rs and 15 more · reported by cisco-skill-scanner, agent-audit-kit, nerlo-behavioral
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/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.
645 AAK-TAINT-002
Files: packages/dart/rust/src/frb_generated.rs, packages/dart/rust/src/lib.rs, packages/ruby/ext/liter_llm_rb/src/lib.rs and 4 more · reported by agent-audit-kit
507 MANIFEST_MISSING_LICENSE
Files: /repo/.codex/skills/api/SKILL.md, /repo/.codex/skills/mcp/SKILL.md, /repo/.codex/skills/cli/SKILL.md and 504 more · reported by cisco-skill-scanner
468 SOCIAL_ENG_VAGUE_DESCRIPTION
Files: /repo/SKILL.md, /repo/plugin/SKILL.md, /repo/packages/python/SKILL.md and 465 more · reported by cisco-skill-scanner
138 HIDDEN_DATA_FILE
Files: /repo/.ai-rulez/config.toml, /repo/plugin/.ai-rulez/config.toml, /repo/.golangci.yml and 87 more · reported by cisco-skill-scanner
12 HIDDEN_EXECUTABLE_SCRIPT
Files: /repo/plugin/.hermes/package/src/liter_llm_hermes_plugin/__init__.py, /repo/plugin/.hermes/plugins/liter-llm/__init__.py, /repo/plugin/.opencode/plugins/liter-llm.js and 3 more · reported by cisco-skill-scanner
Artifact has critical shell execution, credential access, and widespread taint vulnerabilities.
The artifact contains critical command injection vulnerabilities that could lead to shell execution via JavaScript child processes. It also exposes credentials in `crates/liter-llm/src/auth/bedrock_sts.rs` and other locations. Additionally, there are numerous critical taint vulnerabilities, particularly in `crates/liter-llm-node/src/lib.rs` and `crates/liter-llm-proxy/src/config/mod.rs`, which could enable various forms of data manipulation or control flow alteration. Several hidden executable scripts and other credential exposures are also present.
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.
10 BINARY_FILE_DETECTED
Files: /repo/packages/go/.lib/linux-x86_64/libliter_llm_ffi.so, /repo/packages/go/.lib/linux-aarch64/libliter_llm_ffi.so, /repo/packages/go/.lib/macos-arm64/libliter_llm_ffi.dylib and 2 more · reported by cisco-skill-scanner
10 COMMAND_INJECTION_JS_CHILD_PROCESS
Files: /repo/cli-proxy/npm/bin/liter-llm.js, /repo/cli-proxy/npm/install.js, /repo/crates/liter-llm-node/index.js and 2 more · reported by cisco-skill-scanner
10 UNANALYZABLE_BINARY
Files: /repo/packages/go/.lib/windows-x86_64/liter_llm_ffi.dll, /repo/packages/go/.lib/macos-arm64/libliter_llm_ffi.dylib, /repo/packages/go/.lib/linux-x86_64/libliter_llm_ffi.so and 2 more · reported by cisco-skill-scanner
7 EXCESSIVE_FILE_COUNT
Files: /repo/crates/liter-llm/., /repo/packages/elixir/., /repo/packages/java/. and 4 more · reported by cisco-skill-scanner
7 FILE_MAGIC_MISMATCH
Files: /repo/templates/readme/partials/quick_start.md, /repo/templates/readme/partials/installation.md, /repo/llms.txt · reported by cisco-skill-scanner
6 AAK-SECRET-004
Files: crates/liter-llm/src/auth/bedrock_sts.rs, crates/liter-llm/src/auth/azure_ad.rs, crates/liter-llm/src/auth/github_copilot.rs and 1 more · reported by agent-audit-kit
6 YARA_embedded_elf_binary
Files: /repo/packages/go/.lib/linux-aarch64/libliter_llm_ffi.so, /repo/packages/go/.lib/linux-x86_64/libliter_llm_ffi.so · reported by cisco-skill-scanner
6 YARA_embedded_pe_executable
Files: /repo/packages/go/.lib/windows-x86_64/liter_llm_ffi.dll · reported by cisco-skill-scanner
4 AAK-LEGAL-002
Files: package.json, docs-site/package.json, test_apps/wasm/package.json and 1 more · reported by agent-audit-kit
3 DATA_EXFIL_JS_NETWORK
Files: /repo/test_apps/node/globalSetup.ts, /repo/test_apps/wasm/globalSetup.ts, /repo/cli-proxy/npm/install.js · reported by cisco-skill-scanner
3 LOW_ANALYZABILITY
Files: /repo/packages/node, /repo/packages/go, /repo/crates/liter-llm-node · reported by cisco-skill-scanner
3 OVERSIZED_FILE
Files: /repo/packages/go/.lib/macos-arm64/libliter_llm_ffi.dylib, /repo/crates/liter-llm/schemas/catalog.json · reported by cisco-skill-scanner
2 AAK-MARKETPLACE-001
Files: .claude-plugin/marketplace.json, .agents/plugins/marketplace.json · reported by agent-audit-kit
2 AAK-SECRET-003
Files: crates/liter-llm/src/auth/bedrock_sts.rs · reported by agent-audit-kit
2 COMPOUND_EXTRACT_EXECUTE
Files: /repo/plugin/scripts/mcp-launch.sh · reported by cisco-skill-scanner
2 TOOL_ABUSE_UNDECLARED_NETWORK
Files: /repo/repo/ATTRIBUTIONS.md, /repo/cli-proxy/pypi/repo/cli-proxy/pypi/README.md · reported by cisco-skill-scanner
2 YARA_embedded_macho_binary
Files: /repo/packages/go/.lib/macos-x86_64/libliter_llm_ffi.dylib · reported by cisco-skill-scanner
1 AAK-MCP-006
Files: plugin/.mcp.json · reported by agent-audit-kit
1 AAK-MCP-ATTEST-001
Files: plugin/.mcp.json · reported by agent-audit-kit
1 AAK-SUPPLY-005
Files: Cargo.lock · reported by agent-audit-kit
1 DATA_EXFIL_JS_FS_ACCESS
Files: /repo/cli-proxy/npm/install.js · reported by cisco-skill-scanner
Showing 25 of 679; the rest are in the per-scanner reports above.