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.
249 critical findings reported by cisco-skill-scanner, agent-audit-kit, 11 of them in the installed artifact. The composite score alone does not reflect this — read the per-scanner reports below.
github: https://github.com/SamYatesSmith/Tru8, 609 findings
Choose your runtime: the CLI writes the mcpServers config entry for that target.
nerlo install --target claude-code -- tru8
Install respects the composite badge: Clean proceeds, Caution prompts for confirmation, and Flagged is refused. Write operations require an API token.
5 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
40 findings · 1.6s
v2.0.11
236 findings · 49.9s
v0.3.26
302 findings · 50.3s
v0.1.0
20 findings · 68.7s
v0.1.0
11 findings · 68.7s
v0.1.0
This scanner found nothing in this artifact that it assesses. What each scanner covers
0 findings · 12.0s
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 4, 2026 | Scan Halted | — | agentshield: completecisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completenerlo-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 609 findings across every scanner that examined this package. 236 of 249 findings rated critical by their scanner were among the dismissals.
Not reviewed is not the same as clean. Those 18 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.
236 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, agents-claude-md-autorun-1930, AAK-AGENT-002 · Files: .claude/CLAUDE.md, CLAUDE.md · reported by agent-audit-kit, agentshield
80 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, YARA_prompt_injection_unicode_steganography, SECRET_PASSWORD_VAR and 6 more · Files: /repo/backend/tests/unit/services/test_source_monitor.py, /repo/backend/tests/replay_corpus/TRU-93DD-F4B7/cassette.json.gz, /repo/backend/tests/unit/api/test_health_endpoint.py and 9 more · reported by cisco-skill-scanner
45 Documentation or example — The match is in documentation or sample code, confirmed by our own check to be outside the installed artifact.
Rules: opt.nerlo-rules.nerlo-install-run-bundled-artifact, FILE_MAGIC_MISMATCH, AAK-STATE-PRIVACY-001 and 5 more · Files: /repo/docs/guides/quick-start.md, /repo/docs/guides/testing-guide.md, /repo/docs/integration/frontend-backend-integration.md and 19 more · reported by nerlo-install-instruction, cisco-skill-scanner, agent-audit-kit
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.
32 AAK-HEALTHCARE-AI-004
Files: audit/2026-07-23_decoupling_live_test_plan.md, audit/2026-07-24_decoupling_read_layer_design_review.md, audit/2026-05-11_landing_reframe_scope.md and 29 more · reported by agent-audit-kit
21 DATA_EXFIL_JS_NETWORK
Files: /repo/mobile/app/(tabs)/settings.tsx, /repo/mobile/lib/api.ts, /repo/mobile/services/error-reporting.ts and 9 more · reported by cisco-skill-scanner
20 MANIFEST_MISSING_LICENSE
Files: /repo/.claude/skills/phased-build-loop/SKILL.md, /repo/.claude/skills/verify-ui/SKILL.md, /repo/SKILL.md and 17 more · reported by cisco-skill-scanner
18 SOCIAL_ENG_VAGUE_DESCRIPTION
Files: /repo/SKILL.md, /repo/audit/SKILL.md, /repo/backend/SKILL.md and 15 more · reported by cisco-skill-scanner
17 opt.nerlo-rules.nerlo-js-secret-to-network-egress
Files: /repo/mobile/app/(tabs)/settings.tsx, /repo/mobile/lib/api.ts, /repo/mobile/services/error-reporting.ts and 9 more
The model could have called any of these a false positive and did not.
5 AAK-HEALTHCARE-AI-004
Files: docs/SOURCE_REVIEW.md, docs/results-ux-review-2026-06-30/01_DESIGN_DIRECTION.md, docs/page-review-2026-06-29/01_home.md and 2 more · reported by agent-audit-kit
3 AAK-HEALTHCARE-AI-005
Files: docs/legal/2025-01-22_LEGAL_COMPLIANCE_MASTER_PLAN.md, backend/tests/replay_corpus/TRU-B4A3-C42D/input.json, backend/tests/replay_corpus/TRU-B4A3-C42D/golden.json · reported by agent-audit-kit
18 The model called these false positives and our own check did not agree, so the dismissal was refused.
Rules: SECRET_STRIPE_KEY, skills-missing-governance-commands/validate-pr.md, skills-missing-telemetry-commands/verify-implementation.md and 14 more · Files: /repo/docs/integration/SKILL.md, commands/validate-pr.md, commands/verify-implementation.md and 6 more · reported by cisco-skill-scanner, agentshield
Critical command/SQL injection, exposed secrets, and PII handling risks.
The artifact contains critical command injection vulnerabilities in multiple Python scripts, allowing for shell execution. SQL injection vulnerabilities are present in `explore.py` and `audit_extract.py`, which could lead to unauthorized database access. A Stripe key is exposed in `SKILL.md`, and other secrets are found in `api_keys.py` and `climate.py`. Additionally, the artifact handles PII in `eval_classifier_accuracy.py` and has potential for secrets to be sent over the network.
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.
13 HIDDEN_DATA_FILE
Files: /repo/backend/scripts/.opinion_symmetry_eval_questions.json, /repo/backend/scripts/.mapping_sweep_pool.json, /repo/backend/scripts/.opinion_grounds_eval.json and 4 more · reported by cisco-skill-scanner
12 DATA_EXFIL_NETWORK_REQUESTS
Files: /repo/backend/harness/run_golden_dataset.py, /repo/backend/scripts/collect_api_metrics.py, /repo/scripts/check_public_surfaces.py · reported by cisco-skill-scanner
8 AAK-HEALTHCARE-AI-005
Files: audit/2026-06-22_strategic_decision.md, audit/track-n/regression/golden/case-013.json, audit/track-n/audit/reviews/case-011.md and 5 more · reported by agent-audit-kit
6 COMMAND_INJECTION_EVAL
Files: /repo/backend/scripts/causal_specificity_eval.py, /repo/backend/scripts/decompose_symmetry_eval.py, /repo/backend/scripts/extraction_reframe_eval.py · reported by cisco-skill-scanner
6 FILE_MAGIC_MISMATCH
Files: /repo/backend/static/llms.txt, /repo/web/public/llms.txt, /repo/backend/app/templates/pdf/fact_check_report.html and 1 more · reported by cisco-skill-scanner
5 YARA_prompt_injection_unicode_steganography
Files: /repo/web/public/logo.proper.png, /repo/web/public/imagery/choice.tree.png · reported by cisco-skill-scanner
4 AAK-LEGAL-002
Files: package.json, web/package.json, mobile/package.json and 1 more · reported by agent-audit-kit
4 AAK-SECRET-004
Files: web/lib/analytics.ts, mobile/lib/revenuecat.ts, backend/app/api/v1/api_keys.py and 1 more · reported by agent-audit-kit
4 RESOURCE_ABUSE_INFINITE_LOOP
Files: /repo/backend/app/pipeline/progress.py, /repo/backend/app/services/consensus.py · reported by cisco-skill-scanner
3 EXCESSIVE_FILE_COUNT
Files: /repo/., /repo/backend/., /repo/audit/. · reported by cisco-skill-scanner
3 opt.nerlo-rules.nerlo-install-run-bundled-artifact
Files: /repo/audit/OPEN_WORK.md, /repo/backend/README-STARTUP.md · reported by nerlo-install-instruction
3 opt.nerlo-rules.nerlo-py-secret-to-network-egress
Files: /repo/backend/harness/run_golden_dataset.py · reported by nerlo-behavioral
3 TOOL_ABUSE_UNDECLARED_NETWORK
Files: /repo/repo/README.md, /repo/backend/repo/backend/README-STARTUP.md, /repo/backend/tru8_mcp/repo/backend/tru8_mcp/README.md · reported by cisco-skill-scanner
2 AAK-IPI-WILD-CORPUS-001
Files: audit/2026-07-10_usage_ledger_design.md, .claude/settings.json · reported by agent-audit-kit
2 DATA_EXFIL_HTTP_POST
Files: /repo/backend/scripts/collect_api_metrics.py · reported by cisco-skill-scanner
2 hooks-chained-commands-0
Files: settings.json, .claude/settings.json · reported by agentshield
2 hooks-chained-commands-1
Files: settings.json, .claude/settings.json · reported by agentshield
2 hooks-no-pretooluse
Files: settings.local.json, .claude/settings.local.json · reported by agentshield
2 hooks-no-stop-hooks
Files: settings.json, .claude/settings.json · reported by agentshield
2 MANIFEST_INVALID_NAME
Files: /repo/.claude/SKILL.md, /repo/backend/tru8_mcp/SKILL.md · reported by cisco-skill-scanner
2 permissions-missing-deny->-/dev/
Files: settings.json, .claude/settings.json · reported by agentshield
2 permissions-missing-deny-chmod-777
Files: settings.json, .claude/settings.json · reported by agentshield
2 permissions-missing-deny-ssh
Files: settings.json, .claude/settings.json · reported by agentshield
2 permissions-missing-deny-sudo
Files: settings.json, .claude/settings.json · reported by agentshield
2 permissions-no-deny-list
Files: settings.local.json, .claude/settings.local.json · reported by agentshield
2 permissions-permissive-Bash(python -c:*)
Files: settings.local.json, .claude/settings.local.json · reported by agentshield
2 permissions-permissive-Bash(python -m spacy download:*)
Files: settings.local.json, .claude/settings.local.json · reported by agentshield
2 SQL_INJECTION_STRING_FORMAT
Files: /repo/backend/app/services/explore.py · reported by cisco-skill-scanner
2 TOOL_ABUSE_SYSTEM_PACKAGE_INSTALL
Files: /repo/backend/start-backend.sh · reported by cisco-skill-scanner
2 YARA_sql_injection_generic
Files: /repo/backend/scripts/audit_extract.py · reported by cisco-skill-scanner
1 AAK-INDIA-PII-001
Files: backend/scripts/eval_classifier_accuracy.py · reported by agent-audit-kit
1 AAK-SPLUNK-TOKLOG-001
Files: backend/app/services/search.py · reported by agent-audit-kit
1 AAK-SUPPLY-005
Files: package-lock.json · reported by agent-audit-kit
1 AAK-TRUST-004
Files: .claude/settings.local.json · reported by agent-audit-kit
1 AAK-TRUST-006
Files: .claude/settings.local.json · reported by agent-audit-kit
1 LOW_ANALYZABILITY
Files: /repo · reported by cisco-skill-scanner
Showing 25 of 62; the rest are in the per-scanner reports above.