Loading the registry…
Local-first efficiency supervision, regression testing, and verified before/after evaluation for AI agents
Claude Skills are markdown + scripts loaded into Claude Code; scanned with the same pipeline.
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.
9 critical findings reported by cisco-skill-scanner, agent-audit-kit. The composite score alone does not reflect this — read the per-scanner reports below.
Claude Skills install to a single target, no runtime picker.
nerlo install -- tracerazor
Manual alternative: copy the skill folder into ~/.claude/skills/ so Claude Code loads it on next launch.
cp -r -- tracerazor ~/.claude/skills/
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
0 findings · 0.5s
v2.0.11
262 findings · 43.1s
v0.3.74
38 findings · 40.3s
v0.1.0
2 findings · 7.6s
v0.1.0
0 findings · 7.7s
vv0.3.2
No Go packages were found in this artifact. What each scanner covers
0 findings · 0.1s
v0.1.0
This scanner found nothing in this artifact that it assesses. What each scanner covers
0 findings · 10.5s
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 ·n/a: not applicablenerlo-multi-source ·n/a: not applicable | rejected |
| Aug 11, 2026 | Scan Halted | — | agentshield: completecisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completecapslock ·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. None of the 9 findings rated critical by their scanner were dismissed.
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.
9 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 · Files: .github/workflows/tracerazor.yml, .github/workflows/release.yml, .github/workflows/scorecard.yml · reported by agent-audit-kit
8 Documentation or example — The match is in documentation or sample code, confirmed by our own check to be outside the installed artifact.
Rules: AAK-SPLUNK-TOKLOG-001, AAK-HEALTHCARE-AI-004, SOCIAL_ENG_VAGUE_DESCRIPTION and 1 more · Files: examples/demo_online_verification.py, docs/v2_improvement_plan.md, docs/ship_plan.md and 3 more · reported by agent-audit-kit, cisco-skill-scanner
7 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: SECRET_PASSWORD_VAR, AAK-TASKS-003, GLOB_HIDDEN_FILE_TARGETING · Files: /repo/tests/test_mcp_guardrails.py, /repo/tests/test_runtime_persistence.py, tests/test_hf_agentinstruct.py and 1 more · reported by cisco-skill-scanner, agent-audit-kit
2 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-002, TOOL_ABUSE_UNDECLARED_NETWORK · Files: AGENTS.md, /repo/repo/AGENTS.md · reported by agent-audit-kit, 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.
51 HIDDEN_DATA_FILE
Files: /repo/benchmark/trice/results/v2-broad-smoke/tasks/csv-filter/replicate-1/csv-filter/round-1/trice-v2/workspace/.trice/agent_receipt.json, /repo/benchmark/trice/results/v2-broad-smoke/tasks/fix-imports/replicate-1/fix-imports/round-1/baseline-full-context/workspace/.trice/agent_receipt.json, /repo/benchmark/trice/results/v2-broad-smoke/tasks/dedupe-helpers/replicate-1/dedupe-helpers/round-1/baseline-full-context/workspace/.trice/agent_receipt.json and 12 more · reported by cisco-skill-scanner
46 FILE_MAGIC_MISMATCH
Files: /repo/benchmark/__init__.py, /repo/benchmark/data/__init__.py, /repo/tools/__init__.py and 15 more · reported by cisco-skill-scanner
43 MANIFEST_MISSING_LICENSE
Files: /repo/SKILL.md, /repo/benchmark/SKILL.md, /repo/calibration/SKILL.md and 40 more · reported by cisco-skill-scanner
43 SOCIAL_ENG_VAGUE_DESCRIPTION
Files: /repo/SKILL.md, /repo/benchmark/SKILL.md, /repo/calibration/SKILL.md and 40 more · reported by cisco-skill-scanner
17 UNANALYZABLE_BINARY
Critical risks: command injection, path traversal, and credential exposure
The artifact contains critical command injection capabilities via `eval` in `teacher/harness/cache.py`, allowing for shell execution. Multiple path traversal attempts are present in `crates/tracerazor-*` files, which could lead to arbitrary file access. Additionally, credentials may be exposed in `teacher/online.py` and `tracerazor/redundancy/generate_data.py`, with potential network egress of these secrets from `teacher/online.py` and `tracerazor/_audit_client.py`.
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.
15 ARCHIVE_FILE_DETECTED
Files: /repo/paper/trice_suite_evidence.trice.zip, /repo/benchmark/trice/results/v2-suite/trice_suite_evidence.trice.zip, /repo/paper/trice_remote_smoke_evidence.trice.zip and 3 more · reported by cisco-skill-scanner
9 AAK-TASKS-003
Files: benchmark/baselines.py, benchmark/case_study.py, benchmark/tau2_runner.py and 6 more · reported by agent-audit-kit
8 DATA_EXFIL_NETWORK_REQUESTS
Files: /repo/benchmark/hf_loader.py, /repo/tracerazor/_trice/crates.py, /repo/tracerazor/_trice/doctor.py and 2 more · reported by cisco-skill-scanner
7 DATA_EXFIL_JS_NETWORK
Files: /repo/dashboard/src/api.js · reported by cisco-skill-scanner
6 PATH_TRAVERSAL_ATTEMPT
Files: /repo/crates/tracerazor-semantic/SKILL.md, /repo/crates/tracerazor-core/SKILL.md, /repo/crates/tracerazor-cli/SKILL.md and 3 more · reported by cisco-skill-scanner
5 EXCESSIVE_FILE_COUNT
Files: /repo/paper/., /repo/benchmark/trice/results/v2-suite/., /repo/. and 2 more · reported by cisco-skill-scanner
4 TOOL_ABUSE_UNTRUSTED_PACKAGE_SOURCE
Files: /repo/benchmark/tau2_evaluator.py · reported by cisco-skill-scanner
3 AAK-SECRET-004
Files: teacher/online.py, tracerazor/runtime/policy.py, tracerazor/redundancy/generate_data.py · reported by agent-audit-kit
3 MANIFEST_INVALID_NAME
Files: /repo/benchmark/agent_native/SKILL.md, /repo/traces/external/tau_bench/SKILL.md, /repo/traces/external/swe_agent/SKILL.md · reported by cisco-skill-scanner
2 AAK-DNS-REBIND-002
Files: pyproject.toml · reported by agent-audit-kit
2 opt.nerlo-rules.nerlo-py-secret-to-network-egress
Files: /repo/teacher/online.py, /repo/tracerazor/_audit_client.py · reported by nerlo-behavioral
2 RESOURCE_ABUSE_INFINITE_LOOP
Files: /repo/tracerazor/runtime/models.py · reported by cisco-skill-scanner
1 AAK-MCP-006
Files: extensions/claude-code/tracerazor/.mcp.json · reported by agent-audit-kit
1 AAK-MCP-ATTEST-001
Files: extensions/claude-code/tracerazor/.mcp.json · reported by agent-audit-kit
1 AAK-MCP-NOAUTH-DEFAULT
Files: teacher/online.py · reported by agent-audit-kit
1 AAK-MCP-SDK-CVE-2026-52869-001
Files: pyproject.toml · reported by agent-audit-kit
1 AAK-STDIO-001
Files: tracerazor/mcp_server.py · reported by agent-audit-kit
1 AAK-SUPPLY-004
Files: pyproject.toml · reported by agent-audit-kit
1 AAK-SUPPLY-005
Files: Cargo.lock · reported by agent-audit-kit
1 AAK-TAINT-002
Files: crates/tracerazor-cli/src/agent.rs · reported by agent-audit-kit
1 COMMAND_INJECTION_EVAL
Files: /repo/teacher/harness/cache.py · reported by cisco-skill-scanner
1 TOOL_ABUSE_UNDECLARED_NETWORK
Files: /repo/benchmark/repo/benchmark/BENCHMARKS.md · reported by cisco-skill-scanner