Loading the registry…
Semantic codebase search + persistent working memory for AI code editors. Local, zero-config, MCP. No API key.
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.
15 critical findings reported by cisco-skill-scanner. The composite score alone does not reflect this — read the per-scanner reports below.
github: https://github.com/swapnanil/vectr, 526 findings
Choose your runtime: the CLI writes the mcpServers config entry for that target.
nerlo install --target claude-code -- vectr
Install respects the composite badge: Clean proceeds, Caution prompts for confirmation, and Flagged is refused. Write operations require an API token.
4 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.
v2.0.11
467 findings · 129.6s
v0.3.26
39 findings · 126.5s
v0.1.0
5 findings · 58.2s
v0.1.0
15 findings · 58.3s
v1.4.0
This scanner found nothing in this artifact that it assesses. What each scanner covers
0 findings · 0.6s
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 2, 2026 | Scan Halted | — | agentshield ·n/a: not applicablecisco-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 526 findings across every scanner that examined this package. None of the 15 findings rated critical by their scanner were dismissed.
Not reviewed is not the same as clean. Those 8 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.
12 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-SECRET-004, RESOURCE_ABUSE_INFINITE_LOOP, AAK-IPI-WILD-CORPUS-001 and 2 more · Files: tests/test_boundary_precompact.py, /repo/tests/test_longitudinal_scorer.py, tests/test_episode_store.py and 4 more · reported by agent-audit-kit, cisco-skill-scanner
2 Documentation or example — The match is in documentation or sample code, confirmed by our own check to be outside the installed artifact.
Rules: SOCIAL_ENG_VAGUE_DESCRIPTION, MANIFEST_MISSING_LICENSE · Files: /repo/docs/SKILL.md · reported by 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: AAK-GHA-IMMUTABLE-001 · Files: .github/workflows/pypi-publish.yml · reported by 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.
158 DATA_EXFIL_NETWORK_REQUESTS
Files: /repo/benchmarks/anti_memory/arm_store.py, /repo/benchmarks/anti_memory/run_cell.py, /repo/benchmarks/anti_memory/scorer.py and 16 more · reported by cisco-skill-scanner
53 ARCHIVE_FILE_DETECTED
Files: /repo/research/proactive-gate/results/decay-N-20260717-024049-INVALID-THRASH-GUARD/session.jsonl.gz, /repo/research/proactive-gate/results/decay-N-20260717-013455/session.jsonl.gz, /repo/research/proactive-gate/results/decay-M-20260717-192249/session.jsonl.gz and 12 more · reported by cisco-skill-scanner
53 UNANALYZABLE_BINARY
Files: /repo/research/proactive-gate/results/decay-N-20260717-024049-INVALID-THRASH-GUARD/session.jsonl.gz, /repo/research/proactive-gate/results/decay-N-20260717-013455/session.jsonl.gz, /repo/research/proactive-gate/results/decay-M-20260717-192249/session.jsonl.gz and 12 more · reported by cisco-skill-scanner
40 YARA_prompt_injection_unicode_steganography
Files: /repo/research/proactive-gate/results/decay-N-20260717-030703/session.jsonl.gz, /repo/research/proactive-gate/results/decay-N-20260717-030703/transcript.jsonl.gz · reported by cisco-skill-scanner
26
8 The model did not answer for these findings.
Rules: AAK-TASKS-003 · Files: tests/test_task_note_recency.py, tests/test_task_supersedes_hygiene.py, tests/test_proactive_p1_composite.py and 5 more · reported by agent-audit-kit
Critical command injection and SQL injection risks identified.
The artifact contains critical command injection vulnerabilities in JavaScript code within the VSCode extension, allowing shell execution. A critical SQL injection vulnerability is present in Python code in `agent/episode_store.py`. Additionally, the artifact handles secrets and performs dynamic code execution, with multiple instances of potential resource abuse through infinite loops.
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.
Files: /repo/research/proactive-gate/results/decay-M-20260717-192249/preflight.txt, /repo/research/proactive-gate/results/phase1-direct-20260712-112630/preflight.txt, /repo/research/proactive-gate/results/decay-N-20260717-013455/decay-grade-v4-regrade.txt and 5 more · reported by cisco-skill-scanner
24 MANIFEST_MISSING_LICENSE
Files: /repo/SKILL.md, /repo/research/SKILL.md, /repo/vscode-extension/SKILL.md and 21 more · reported by cisco-skill-scanner
24 SOCIAL_ENG_VAGUE_DESCRIPTION
Files: /repo/SKILL.md, /repo/research/SKILL.md, /repo/vscode-extension/SKILL.md and 21 more · reported by cisco-skill-scanner
15 opt.nerlo-rules.nerlo-install-run-bundled-artifact
Files: /repo/benchmarks/camel/README.md, /repo/benchmarks/longitudinal_rediscovery/DESIGN.md, /repo/research/brain-memory/delivery-not-storage.md and 9 more · reported by nerlo-install-instruction
12 YARA_prompt_injection_generic
Files: /repo/benchmarks/uv/run5_20260603_134810.json · reported by cisco-skill-scanner
11 RESOURCE_ABUSE_INFINITE_LOOP
Files: /repo/agent/working_context_store/_store.py, /repo/benchmarks/anti_memory/scorer.py, /repo/benchmarks/longitudinal_rediscovery/scorer.py and 1 more · reported by cisco-skill-scanner
10 AAK-HEALTHCARE-AI-004
Files: research/README.md, research/proactive-gate/protocol.md, research/proactive-gate/decay-protocol.md and 7 more · reported by agent-audit-kit
10 AAK-TASKS-003
Files: benchmarks/vs_bash/run_tier0.py, benchmarks/harness/scoring.py, benchmarks/harness/tasks.py and 7 more · reported by agent-audit-kit
10 MANIFEST_INVALID_NAME
Files: /repo/research/proactive-gate/results/decay-N-20260717-010533-INVALID-SAMPLING/SKILL.md, /repo/research/proactive-gate/results/decay-N-20260717-030703/SKILL.md, /repo/research/proactive-gate/results/decay-N-20260717-005930-INVALID-SHORTCUT/SKILL.md and 7 more · reported by cisco-skill-scanner
8 TOOL_ABUSE_UNDECLARED_NETWORK
Files: /repo/repo/CHANGELOG.md, /repo/benchmarks/repo/benchmarks/README.md, /repo/benchmarks/longitudinal_rediscovery/repo/benchmarks/longitudinal_rediscovery/DESIGN.md and 5 more · reported by cisco-skill-scanner
7 AAK-SECRET-004
Files: app/service.py, benchmarks/cpython/run3_20260602_090343_additive.json, benchmarks/cpython/run3_20260602_001907_additive.json and 1 more · reported by agent-audit-kit
6 DATA_EXFIL_JS_FS_ACCESS
Files: /repo/vscode-extension/src/extension.ts · reported by cisco-skill-scanner
6 DATA_EXFIL_JS_NETWORK
Files: /repo/vscode-extension/src/extension.ts · reported by cisco-skill-scanner
6 LOW_ANALYZABILITY
Files: /repo/research/proactive-gate/results/decay-N-20260717-013455, /repo/research/proactive-gate/results/decay-M-20260717-192249, /repo/research/proactive-gate/results/decay-N-20260717-024049-INVALID-THRASH-GUARD and 3 more · reported by cisco-skill-scanner
5 OVERSIZED_FILE
Files: /repo/research/proactive-gate/results/decay-M-20260717-192249/transcript.jsonl.gz, /repo/research/proactive-gate/results/decay-N-20260717-030703/transcript.jsonl.gz · reported by cisco-skill-scanner
5 PIPELINE_TAINT_FLOW
Files: /repo/agent/config.yaml, /repo/app/cmdnorm.py, /repo/benchmarks/arc_replay_results.md and 1 more · reported by cisco-skill-scanner
3 EXCESSIVE_FILE_COUNT
Files: /repo/research/., /repo/research/proactive-gate/., /repo/. · reported by cisco-skill-scanner
2 COMMAND_INJECTION_JS_CHILD_PROCESS
Files: /repo/vscode-extension/src/extension.ts · reported by cisco-skill-scanner
2 HIDDEN_DATA_FILE
Files: /repo/vscode-extension/.vscodeignore · reported by cisco-skill-scanner
2 opt.nerlo-rules.nerlo-py-dynamic-exec
Files: /repo/benchmarks/longitudinal_rediscovery/run_leg.py, /repo/benchmarks/vs_bash/run_tier0.py · reported by nerlo-behavioral
2 opt.nerlo-rules.nerlo-py-secret-to-network-egress
Files: /repo/main.py · reported by nerlo-behavioral
1 AAK-SUPPLY-004
Files: pyproject.toml · reported by agent-audit-kit
1 opt.nerlo-rules.nerlo-dynamic-exec
Files: /repo/vscode-extension/src/extension.ts · reported by nerlo-behavioral
1 SQL_INJECTION_STRING_FORMAT
Files: /repo/agent/episode_store.py · reported by cisco-skill-scanner
Showing 25 of 38; the rest are in the per-scanner reports above.