Loading the registry…
Local-first command wrapper for AI coding agents with compressed terminal output and privacy-safe proof metrics.
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.
60 critical findings reported by cisco-skill-scanner, agent-audit-kit, 6 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/PsYcGoD/sage, 183 findings
Choose your runtime: the CLI writes the mcpServers config entry for that target.
nerlo install --target claude-code -- psycgod-sage
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
0 findings · 0.6s
v2.0.11
63 findings · 13.2s
v0.3.26
76 findings · 10.8s
v0.1.0
10 findings · 33.8s
v0.1.0
0 findings · 33.8s
v0.1.0
0 findings · 25.5s
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 149 findings across every scanner that examined this package. 54 of 60 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.
55 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, TOOL_ABUSE_UNDECLARED_NETWORK · Files: AGENTS.md, CLAUDE.md, /repo/repo/AGENTS.md · reported by agent-audit-kit, cisco-skill-scanner
15 Documentation or example — The match is in documentation or sample code, confirmed by our own check to be outside the installed artifact.
Rules: UNANALYZABLE_BINARY, SOCIAL_ENG_VAGUE_DESCRIPTION, MANIFEST_MISSING_LICENSE and 2 more · Files: /repo/docs/assets/sage-30s-real-demo.mp4, /repo/docs/SKILL.md, /repo/.github/SKILL.md and 3 more · reported by cisco-skill-scanner
13 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-002, AAK-SECRET-004, SECRET_PASSWORD_VAR and 1 more · Files: js/tests/agents.test.ts, tests/test_security_privacy.py, /repo/js/tests/agents.test.ts and 1 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: 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.
10 DATA_EXFIL_JS_NETWORK
Files: /repo/cloudflare/sage-api/src/worker.js · reported by cisco-skill-scanner
6 AAK-TASKS-003
Files: src/sage/store.py, src/sage/cli.py, src/sage/agents/base_agent.py and 3 more · reported by agent-audit-kit
6 opt.nerlo-rules.nerlo-py-secret-to-network-egress
Files: /repo/src/sage/telemetry.py · reported by nerlo-behavioral
5 DATA_EXFIL_NETWORK_REQUESTS
Files: /repo/src/sage/github_oauth.py, /repo/src/sage/mcp/client.py · reported by cisco-skill-scanner
4 COMMAND_INJECTION_JS_CHILD_PROCESS
Files: /repo/js/src/python/bridge.ts · reported by cisco-skill-scanner
4 DATA_EXFIL_SOCKET_CONNECT
The model could have called any of these a false positive and did not.
1 AAK-TASKS-003
Files: src/sage/agents/specialized/test_agent.py · reported by agent-audit-kit
Critical risks: command injection, exposed secrets, and network egress.
The artifact exhibits critical command injection capabilities via JavaScript child processes in `/repo/js/src/python/bridge.ts`. It contains exposed secrets, including a GitHub token in `/repo/src/sage/agents/evaluation.py` and another secret in `src/sage/agents/evaluation.py`. Furthermore, the artifact can perform network egress using secrets from `/repo/cloudflare/sage-api/src/worker.js` and `/repo/src/sage/telemetry.py`. Other high-severity findings include sensitive data processing, task queue manipulation, and Splunk token logging.
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.
4 MANIFEST_MISSING_LICENSE
Files: /repo/SKILL.md, /repo/scripts/SKILL.md, /repo/js/SKILL.md and 1 more · reported by cisco-skill-scanner
4 SOCIAL_ENG_VAGUE_DESCRIPTION
Files: /repo/SKILL.md, /repo/scripts/SKILL.md, /repo/js/SKILL.md and 1 more · reported by cisco-skill-scanner
3 BINARY_FILE_DETECTED
Files: /repo/codex-ab-proof/with-sage-codex.jsonl, /repo/codex-ab-proof/codex-ab-report.json, /repo/codex-ab-proof/without-sage-codex.jsonl · reported by cisco-skill-scanner
3 UNANALYZABLE_BINARY
Files: /repo/codex-ab-proof/with-sage-codex.jsonl, /repo/codex-ab-proof/without-sage-codex.jsonl, /repo/codex-ab-proof/codex-ab-report.json · reported by cisco-skill-scanner
2 AAK-IPI-WILD-CORPUS-001
Files: src/sage/agentic/engine.py, src/sage/ml/predictors/permission_predictor.py · reported by agent-audit-kit
2 LOW_ANALYZABILITY
Files: /repo/js, /repo/cloudflare/sage-api · reported by cisco-skill-scanner
2 opt.nerlo-rules.nerlo-hardcoded-external-egress
Files: /repo/cloudflare/sage-api/src/worker.js · reported by nerlo-behavioral
2 opt.nerlo-rules.nerlo-js-secret-to-network-egress
Files: /repo/cloudflare/sage-api/src/worker.js · reported by nerlo-behavioral
1 AAK-SECRET-008
Files: src/sage/agents/evaluation.py · reported by agent-audit-kit
1 AAK-SPLUNK-TOKLOG-001
Files: src/sage/cli.py · reported by agent-audit-kit
1 AAK-SUPPLY-004
Files: pyproject.toml · reported by agent-audit-kit
1 AAK-TASKS-001
Files: src/sage/agents/task_queue.py · reported by agent-audit-kit
1 EXCESSIVE_FILE_COUNT
Files: /repo/. · reported by cisco-skill-scanner
1 HIDDEN_DATA_FILE
Files: /repo/.mailmap · reported by cisco-skill-scanner
1 SECRET_GITHUB_TOKEN
Files: /repo/src/sage/agents/evaluation.py · reported by cisco-skill-scanner