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.
475 critical findings reported by agent-audit-kit, 17 of them in the installed artifact. The composite score alone does not reflect this — read the per-scanner reports below.
This artifact ships from 2 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.
github: https://github.com/Eilodon/CALM, 726 findings
Choose your runtime: the CLI writes the mcpServers config entry for that target.
nerlo install --target claude-code -- CALM
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
Incomplete run
0 findings · 0.8s
v2.0.11
121 findings · 27.0s
v0.3.26
546 findings · 12.6s
v0.1.0
0 findings · 29.6s
v0.1.0
25 findings · 29.6s
v0.1.0
0 findings · 21.9s
No report in this scan: capslock, 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 |
|---|---|---|---|---|
| Aug 3, 2026 | Scan Halted | — | agentshield ·!: incompletecisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completenerlo-multi-source: complete | rejected |
| Aug 1, 2026 | Scan Halted | — | agentshield ·!: incompletecisco-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 692 findings across every scanner that examined this package. 458 of 475 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.
456 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, AAK-AGENT-003 · Files: AGENTS.md · reported by agent-audit-kit
97 Documentation or example — The match is in documentation or sample code, confirmed by our own check to be outside the installed artifact.
Rules: PROMPT_INJECTION_IGNORE_INSTRUCTIONS, AAK-IPI-WILD-CORPUS-001, opt.nerlo-rules.nerlo-install-fetch-raw-then-run and 10 more · Files: /repo/AGENTS.md, /repo/docs/SKILL.md, /repo/docs/architecture.md and 45 more · reported by cisco-skill-scanner, agent-audit-kit, 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: AAK-TAINT-002, AAK-TAINT-001, AAK-LEGAL-002 and 1 more · Files: crates/calm-cli/tests/sigterm_shutdown.rs, crates/calm-cli/tests/daemon_integration.rs, tests/js_client_interop/package.json and 3 more · reported by agent-audit-kit, cisco-skill-scanner
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: FILE_MAGIC_MISMATCH · Files: /repo/.github/workflows/windows-build-experiment.yml · 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.
18 MANIFEST_MISSING_LICENSE
Files: /repo/plugins/calm/skills/calm-guide/SKILL.md, /repo/.claude/skills/calm-guide/SKILL.md, /repo/.claude/skills/vheatm/SKILL.md and 15 more · reported by cisco-skill-scanner
15 SOCIAL_ENG_VAGUE_DESCRIPTION
Files: /repo/SKILL.md, /repo/npm/SKILL.md, /repo/benchmarks/SKILL.md and 12 more · reported by cisco-skill-scanner
14 AAK-SECRET-004
Files: crates/calm-core/src/sanitize.rs, crates/calm-core/src/memory.rs, crates/calm-core/src/lsp/overlay.rs and 1 more · reported by agent-audit-kit
13 AAK-HEALTHCARE-AI-004
Files: benchmarks/b12_tier1_tier2_tool_correctness/FINDINGS_ROOTCAUSE.md, .claude/skills/vheatm/SKILL.md, .claude/skills/vheatm/references/16-temporal-scan-mode.md and 10 more · reported by agent-audit-kit
9 MANIFEST_INVALID_NAME
Files: /repo/benchmarks/b7_task_correctness/SKILL.md, /repo/benchmarks/b11_extended_competitor_ab/SKILL.md, /repo/benchmarks/b12_tier1_tier2_tool_correctness/SKILL.md and 6 more
Sensitive data exposure and potential for code execution.
The artifact contains critical findings related to credential access and tainted data flow within its core components, specifically in `crates/calm-core/src/sanitize.rs` and `crates/calm-server/src/daemon.rs`. Multiple high-severity findings indicate further credential exposure in `crates/calm-cli/src/main.rs` and `crates/calm-core/src/lsp/overlay.rs`. There are also high-severity supply chain risks identified in `.mcp.json` and potential for shell execution via compound extract and execute operations.
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.
6 AAK-SECRET-008
Files: crates/calm-core/src/sanitize.rs · reported by agent-audit-kit
5 AAK-MCP-007
Files: .mcp.json, plugins/calm/.mcp.json · reported by agent-audit-kit
4 AAK-MCP-006
Files: .mcp.json, .cursor/mcp.json · reported by agent-audit-kit
4 COMPOUND_EXTRACT_EXECUTE
Files: /repo/npm/stage-release.sh, /repo/scripts/install.sh, /repo/scripts/mcp-launcher.sh · reported by cisco-skill-scanner
4 PIPELINE_TAINT_FLOW
Files: /repo/llms.txt, /repo/scripts/install.sh, /repo/README.md and 1 more · reported by cisco-skill-scanner
3 AAK-SECRET-003
Files: crates/calm-core/src/sanitize.rs · reported by agent-audit-kit
3 FILE_MAGIC_MISMATCH
Files: /repo/benchmarks/lib/refactor_tasks.yaml, /repo/llms.txt · reported by cisco-skill-scanner
3 opt.nerlo-rules.nerlo-install-fetch-raw-then-run
Files: /repo/README.md, /repo/llms.txt, /repo/scripts/install.sh · reported by nerlo-install-instruction
3 opt.nerlo-rules.nerlo-install-pipe-to-shell
Files: /repo/README.md, /repo/llms.txt, /repo/scripts/install.sh · reported by nerlo-install-instruction
2 AAK-MCP-002
Files: .mcp.json, .cursor/mcp.json · reported by agent-audit-kit
2 AAK-MCP-005
Files: .mcp.json, plugins/calm/.mcp.json · reported by agent-audit-kit
2 AAK-SECRET-002
Files: crates/calm-core/src/sanitize.rs · reported by agent-audit-kit
2 AAK-SUPPLY-001
Files: .mcp.json · reported by agent-audit-kit
2 AAK-TAINT-001
Files: crates/calm-core/src/scip/runner.rs, crates/calm-server/src/daemon.rs · reported by agent-audit-kit
2 AAK-TAINT-002
Files: crates/calm-server/src/lib.rs, crates/calm-server/src/daemon.rs · reported by agent-audit-kit
2 HIDDEN_EXECUTABLE_SCRIPT
Files: /repo/.agents/hooks/calm-guard.sh, /repo/.agents/hooks/calm-guard-probe.sh · reported by cisco-skill-scanner
1 AAK-HEALTHCARE-AI-005
Files: .claude/skills/vheatm/references/03-ux-lens.md · reported by agent-audit-kit
1 AAK-IPI-WILD-CORPUS-001
Files: crates/calm-core/assets/potion-code-16m/tokenizer.json · reported by agent-audit-kit
1 AAK-MARKETPLACE-001
Files: .claude-plugin/marketplace.json · reported by agent-audit-kit
1 AAK-SUPPLY-005
Files: Cargo.lock · reported by agent-audit-kit
1 AAK-TASKS-003
Files: benchmarks/b10_real_competitor_ab/run_benchmark.py · reported by agent-audit-kit
1 AAK-TRUST-007
Files: .claude/settings.json · reported by agent-audit-kit
1 EXCESSIVE_FILE_COUNT
Files: /repo/. · reported by cisco-skill-scanner
1 HIDDEN_DATA_FILE
Files: /repo/.agents/hooks.json · reported by cisco-skill-scanner
1 LOW_ANALYZABILITY
Files: /repo/npm · reported by cisco-skill-scanner
1 PROMPT_INJECTION_IGNORE_INSTRUCTIONS
Files: /repo/SKILL.md · reported by cisco-skill-scanner
Showing 25 of 51; the rest are in the per-scanner reports above.