Loading the registry…
Agents make claims, Reelier writes receipts - record an agent workflow once, replay it deterministically at 0 tokens, and get an asserted receipt on every run.
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.
200 critical findings reported by cisco-skill-scanner, agent-audit-kit, 10 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/seldonframe/reelier, 392 findings
Choose your runtime: the CLI writes the mcpServers config entry for that target.
nerlo install --target claude-code -- reelier
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
2 findings · 0.8s
v2.0.11
167 findings · 23.6s
v0.3.26
164 findings · 9.9s
v0.1.0
10 findings · 35.4s
v0.1.0
1 finding · 35.4s
v0.1.0
1 finding · 22.7s
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: completecisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completenerlo-multi-source: complete | rejected |
| Aug 1, 2026 | Scan Halted | — | agentshield: completecisco-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 345 findings across every scanner that examined this package. 190 of 200 findings rated critical by their scanner were among the dismissals.
Not reviewed is not the same as clean. Those 1 finding 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.
134 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 · Files: CLAUDE.md · reported by agent-audit-kit
61 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, AAK-SECRET-004, FILE_MAGIC_MISMATCH and 1 more · Files: /repo/test/compile.test.ts, /repo/test/golden.test.ts, /repo/test/init.test.ts and 5 more · reported by cisco-skill-scanner, agent-audit-kit
38 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-pipe-to-shell, AAK-HEALTHCARE-AI-004, PIPELINE_TAINT_FLOW and 3 more · Files: /repo/examples/gbrain/README.md, docs/specs/argument-provenance-v1.md, docs/specs/artifact-attestation-v1.md and 19 more · reported by nerlo-install-instruction, agent-audit-kit, cisco-skill-scanner
10 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, FILE_MAGIC_MISMATCH, MANIFEST_INVALID_NAME · Files: .github/workflows/reelier-replay.example.yml, .github/workflows/reelier-bump-check.yml, .github/workflows/gbrain-state-e2e.yml and 3 more · 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.
14 HIDDEN_DATA_FILE
Files: /repo/.superpowers/sdd/trust-sliceB-review.md, /repo/.reelier/scope.yml, /repo/.superpowers-wc/wc2-report.md and 11 more · reported by cisco-skill-scanner
12 MANIFEST_MISSING_LICENSE
Files: /repo/skills/reelier/SKILL.md, /repo/clawhub/reelier/SKILL.md, /repo/integrations/claude-code/reelier/SKILL.md and 9 more · reported by cisco-skill-scanner
8 SOCIAL_ENG_VAGUE_DESCRIPTION
Files: /repo/SKILL.md, /repo/.superpowers-tq/SKILL.md, /repo/.superpowers-wc/SKILL.md and 5 more · reported by cisco-skill-scanner
7 DATA_EXFIL_JS_NETWORK
Files: /repo/src/get.ts, /repo/src/llm.ts, /repo/src/push.ts and 1 more · reported by cisco-skill-scanner
6 COMMAND_INJECTION_EVAL
Files: /repo/src/cli.ts, /repo/src/compile.ts, /repo/src/init.ts and 1 more · reported by cisco-skill-scanner
The model could have called any of these a false positive and did not.
16 DATA_EXFIL_JS_NETWORK
Files: /repo/.github/scripts/gha-pr-comment.mjs, /repo/examples/benchmark/agent-arm.mjs, /repo/examples/benchmark/bench.mjs and 3 more · reported by cisco-skill-scanner
3 opt.nerlo-rules.nerlo-js-secret-to-network-egress
Files: /repo/.github/scripts/gha-pr-comment.mjs, /repo/examples/benchmark/agent-arm.mjs, /repo/examples/benchmark/task2-agent-arm.mjs · reported by nerlo-behavioral
2 opt.nerlo-rules.nerlo-hardcoded-external-egress
Files: /repo/examples/benchmark/agent-arm.mjs, /repo/examples/benchmark/task2-agent-arm.mjs · reported by nerlo-behavioral
1 The model did not answer for these findings.
Rules: LOW_ANALYZABILITY · Files: /repo/.github · reported by cisco-skill-scanner
Critical command injection and secret network egress risks
The artifact contains multiple critical command injection vulnerabilities in `src/cli.ts`, `src/compile.ts`, `src/init.ts`, `src/session.ts`, and various scripts, allowing for potential shell execution. It also exhibits high-severity findings related to network egress of secrets from `src/get.ts`, `src/llm.ts`, and benchmark examples. Additionally, sensitive data is present in `contract/wire-contract.v1.json` and `src/artifact.ts`, and OAuth tokens are handled in `src/login.ts`.
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/src/get.ts, /repo/src/llm.ts, /repo/src/push.ts · reported by nerlo-behavioral
3 AAK-ANTHROPIC-SDK-001
Files: scripts/demo-downstream.js, src/mcp-client.ts, src/cli.ts · reported by agent-audit-kit
3 AAK-SECRET-004
Files: src/artifact.ts, src/effect-verbs.ts, contract/wire-contract.v1.json · reported by agent-audit-kit
3 COMMAND_INJECTION_JS_CHILD_PROCESS
Files: /repo/scripts/e2e-local.mjs, /repo/scripts/run-fuzz.mjs, /repo/scripts/preflight.mjs · reported by cisco-skill-scanner
2 AAK-HEALTHCARE-AI-004
Files: CHANGELOG.md, SPEC.md · reported by agent-audit-kit
2 AAK-MCP-007
Files: .mcp.json · reported by agent-audit-kit
2 AAK-SUPPLY-001
Files: .mcp.json · reported by agent-audit-kit
2 MANIFEST_INVALID_NAME
Files: /repo/.superpowers-tq/SKILL.md, /repo/.superpowers-wc/SKILL.md · reported by cisco-skill-scanner
1 AAK-MCP-005
Files: .mcp.json · reported by agent-audit-kit
1 AAK-MCP-STDIO-CMD-INJ-002
Files: scripts/demo-downstream.js · reported by agent-audit-kit
1 AAK-OAUTH-001
Files: src/login.ts · reported by agent-audit-kit
1 AAK-OAUTH-3P-001
Files: package.json · reported by agent-audit-kit
1 AAK-SECRET-005
Files: contract/wire-contract.v1.public-key.pem · reported by agent-audit-kit
1 AAK-SUPPLY-005
Files: package-lock.json · reported by agent-audit-kit
1 EXCESSIVE_FILE_COUNT
Files: /repo/. · reported by cisco-skill-scanner
1 LOW_ANALYZABILITY
Files: /repo · reported by cisco-skill-scanner
1 nerlo-malware-obfuscated_blob
Files: npm@0.30.0:contract/wire-contract.v1.json · reported by nerlo-malware
1 skills-missing-governance-skills/sf-post-deploy-smoke.skill.md
Files: skills/sf-post-deploy-smoke.skill.md · reported by agentshield
1 skills-missing-telemetry-skills/sf-post-deploy-smoke.skill.md
Files: skills/sf-post-deploy-smoke.skill.md · reported by agentshield
Showing 25 of 28; the rest are in the per-scanner reports above.