Loading the registry…
Native Pi integration for the MAINFRAME agent-safe Bash runtime
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.
135 critical findings reported by cisco-skill-scanner, agent-audit-kit, 70 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/gtwatts/mainframe, 635 findings
Choose your runtime: the CLI writes the mcpServers config entry for that target.
nerlo install --target claude-code -- @gtwatts/mainframe-pi
Install respects the composite badge: Clean proceeds, Caution prompts for confirmation, and Flagged is refused. Write operations require an API token.
7 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
6 findings · 0.8s
v2.0.11
425 findings · 50.5s
v0.3.74
27 findings · 51.7s
v0.1.0
0 findings · 16.1s
v0.1.0
104 findings · 16.1s
vv0.3.2
Incomplete run
0 findings · 0.8s
v0.1.0
0 findings · 18.7s
No report in this scan: 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 22, 2026 | Scan Halted | — | agentshield: completecisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completecapslock ·!: incompletenerlo-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 562 findings across every scanner that examined this package. 65 of 135 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.
191 Documentation or example — The match is in documentation or sample code, confirmed by our own check to be outside the installed artifact.
Rules: COMPOUND_FIND_EXEC, COMPOUND_FETCH_EXECUTE, opt.nerlo-rules.nerlo-install-reverse-shell-directive and 15 more · Files: /repo/docs/AI_NATIVE_BASH_VISION_V10.md, /repo/docs/SKILL.md, /repo/docs/V10_ENGINEERING_PLAN.md and 55 more · reported by cisco-skill-scanner, nerlo-install-instruction, agent-audit-kit
121 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_JS_FUNCTION_CONSTRUCTOR, YARA_command_injection_generic, COMMAND_INJECTION_JS_CHILD_PROCESS and 12 more · Files: /repo/lsp/src/__tests__/integration/server.test.ts, /repo/lsp/src/__tests__/unit/metadata.test.ts, /repo/bindings/nodejs/tests/validation.test.ts and 18 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, agents-time-bomb-4355 · Files: CLAUDE.md · reported by agent-audit-kit, agentshield
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: MANIFEST_INVALID_NAME · Files: /repo/.github/SKILL.md · reported by 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.
30 MANIFEST_MISSING_LICENSE
Files: /repo/skills/claude-code/SKILL.md, /repo/skills/pi/SKILL.md, /repo/skills/mainframe/SKILL.md and 27 more · reported by cisco-skill-scanner
24 SOCIAL_ENG_VAGUE_DESCRIPTION
Files: /repo/SKILL.md, /repo/control_plane/SKILL.md, /repo/skills/SKILL.md and 21 more · reported by cisco-skill-scanner
23 TOOL_ABUSE_SYSTEM_MODIFICATION
Files: /repo/lib/capability.sh, /repo/lib/guard_enhanced.sh, /repo/lib/risk.sh and 10 more · reported by cisco-skill-scanner
20 DATA_EXFIL_NETWORK_REQUESTS
Files: /repo/control_plane/mainframe_control_plane/cli.py, /repo/control_plane/mainframe_control_plane/coding.py, /repo/control_plane/mainframe_control_plane/kernel.py and 2 more · reported by cisco-skill-scanner
15 FIND_EXEC_PATTERN
Files: /repo/lib/compat.sh, /repo/lib/optimize.sh, /repo/lib/ammma_tiers.sh and 5 more · reported by cisco-skill-scanner
The model could have called any of these a false positive and did not.
3 PIPELINE_TAINT_FLOW
Files: /repo/lib/tirith_pipe.sh · reported by cisco-skill-scanner
1 The model did not answer for these findings.
Rules: BINARY_FILE_DETECTED · Files: /repo/demos/tapes/commercial/demos/captures/demo-scene.mp4 · reported by cisco-skill-scanner
Artifact contains multiple critical command injection vulnerabilities.
The artifact exhibits critical command injection vulnerabilities, particularly in Node.js bindings within `src/core.ts` and `src/utils.ts`, allowing for shell execution via child processes and function constructors. Generic command injection patterns are also present in validation scripts across Node.js and Python bindings. Additionally, the artifact contains patterns indicative of credential harvesting and system modification capabilities.
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.
12 COMMAND_INJECTION_JS_FUNCTION_CONSTRUCTOR
Files: /repo/bindings/nodejs/src/utils.ts · reported by cisco-skill-scanner
11 COMMAND_INJECTION_JS_CHILD_PROCESS
Files: /repo/skills/pi/extensions/mainframe.ts, /repo/bindings/nodejs/src/core.ts, /repo/evals/agent-impact/runners/pi-awm-transition-driver.mjs · reported by cisco-skill-scanner
10 AAK-SECRET-004
Files: lib/agent_safety.sh, lib/immutable.sh, lib/burl_ai.sh and 3 more · reported by agent-audit-kit
8 YARA_command_injection_generic
Files: /repo/benchmarks/validation_functions.bench.sh, /repo/bindings/python/mainframe_bash/validation.py, /repo/bindings/nodejs/src/validation.ts and 2 more · reported by cisco-skill-scanner
6 DATA_EXFIL_JS_FS_ACCESS
Files: /repo/lsp/src/index.ts, /repo/lsp/src/metadata.ts, /repo/lsp/src/server.ts · reported by cisco-skill-scanner
6 SECRET_PASSWORD_VAR
Files: /repo/lib/agent_safety.sh, /repo/lib/burl_ai.sh, /repo/lib/vectordb.sh · reported by cisco-skill-scanner
6 YARA_sql_injection_generic
Files: /repo/lib/guard_enhanced.sh · reported by cisco-skill-scanner
5 FILE_MAGIC_MISMATCH
Files: /repo/skills/aider/.aider.conf.yml, /repo/bindings/nodejs/src/index.ts · reported by cisco-skill-scanner
5 HIDDEN_DATA_FILE
Files: /repo/skills/aider/.aider.conf.yml, /repo/lsp/.vscodeignore · reported by cisco-skill-scanner
5 opt.nerlo-rules.nerlo-install-pipe-to-shell
Files: /repo/CHEATSHEET.md, /repo/DECISION_TREES.md · reported by nerlo-install-instruction
5 opt.nerlo-rules.nerlo-install-shell-inline-command
Files: /repo/ROADMAP.md, /repo/reviews/BASH_UNIX_REVIEW.md, /repo/reviews/SECURITY_REVIEW.md · reported by nerlo-install-instruction
4 COMMAND_INJECTION_EVAL
Files: /repo/skills/pi/extensions/mainframe.ts, /repo/security/gate-normalizer.mjs · reported by cisco-skill-scanner
4 RESOURCE_ABUSE_FORK_BOMB
Files: /repo/lib/predict.sh, /repo/lib/verify.sh, /repo/scripts/export-gate-rules.py · reported by cisco-skill-scanner
4 TOOL_ABUSE_SYSTEM_PACKAGE_INSTALL
Files: /repo/install.sh, /repo/lib/sandbox.sh, /repo/scripts/agent/self-heal.sh · reported by cisco-skill-scanner
3 COMMAND_INJECTION_USER_INPUT
Files: /repo/lib/fluent.sh, /repo/scripts/generate-eval-audit.sh, /repo/lib/proptest.sh · reported by cisco-skill-scanner
3 LOW_ANALYZABILITY
Files: /repo/lsp, /repo/bindings/nodejs, /repo/skills/pi · reported by cisco-skill-scanner
3 opt.nerlo-rules.nerlo-install-run-bundled-artifact
Files: /repo/CONTRIBUTING.md, /repo/lsp/IMPLEMENTATION.md · reported by nerlo-install-instruction
2 AAK-IPI-WILD-CORPUS-001
Files: FUNCTIONS.lsp.json, reviews/IMPLEMENTATION_SUMMARY_v7.md · reported by agent-audit-kit
2 AAK-MCP-ARGV-TOCTOU-001
Files: skills/pi/extensions/mainframe.ts, bindings/nodejs/src/core.ts · reported by agent-audit-kit
2 AAK-SKILL-UNTRUSTED-EXEC-PATH
Files: lib/heal.sh, scripts/export-gate-rules.py · reported by agent-audit-kit
2 COMPOUND_EXTRACT_EXECUTE
Files: /repo/lib/compat.sh, /repo/scripts/dev/certify-shell-onboarding.sh · reported by cisco-skill-scanner
2 OBFUSCATION_XOR_ENCODING
Files: /repo/scripts/dev/build-release-tar.py, /repo/scripts/dev/native-host/build-release-evidence.py · reported by cisco-skill-scanner
2 PIPELINE_TAINT_FLOW
Files: /repo/lib/tirith_pipe.sh · reported by cisco-skill-scanner
2 RESOURCE_ABUSE_INFINITE_LOOP
Files: /repo/mcp/src/mainframe_mcp/runtime_root.py · reported by cisco-skill-scanner
1 AAK-LEGAL-002
Files: scripts/dev/native-host/package.json · reported by agent-audit-kit
1 AAK-OAUTH-005
Files: scripts/dev/native-host/claude-messages-server.py · reported by agent-audit-kit
1 AAK-SUPPLY-004
Files: package.json · reported by agent-audit-kit
1 COMPOUND_FIND_EXEC
Files: /repo/lib/compat.sh · reported by cisco-skill-scanner
1 EXCESSIVE_FILE_COUNT
Files: /repo/. · reported by cisco-skill-scanner
1 GLOB_HIDDEN_FILE_TARGETING
Files: /repo/scripts/file/bulk-rename.sh · reported by cisco-skill-scanner
1 hooks-bg-process-3133
Files: hooks/agent-gateway.sh · reported by agentshield
1 hooks-bg-process-3194
Files: hooks/agent-gateway.sh · reported by agentshield
1 hooks-bg-process-5731
Files: hooks/agent-gateway.sh · reported by agentshield
1 MANIFEST_INVALID_NAME
Files: /repo/control_plane/SKILL.md · reported by cisco-skill-scanner
1 opt.nerlo-rules.nerlo-install-reverse-shell-directive
Files: /repo/reviews/SECURITY_REVIEW.md · reported by nerlo-install-instruction
1 PROMPT_INJECTION_IGNORE_INSTRUCTIONS
Files: /repo/reviews/SKILL.md · reported by cisco-skill-scanner
1 skills-missing-governance-skills/README.md
Files: skills/README.md · reported by agentshield
1 skills-missing-telemetry-skills/README.md
Files: skills/README.md · reported by agentshield
1 TOOL_ABUSE_UNDECLARED_NETWORK
Files: /repo/repo/CHANGELOG.md · reported by cisco-skill-scanner
1 TOOL_ABUSE_UNTRUSTED_PACKAGE_SOURCE
Files: /repo/lib/tirith_ecosystem.sh · reported by cisco-skill-scanner
1 YARA_credential_harvesting_generic
Files: /repo/lib/guard_enhanced.sh · reported by cisco-skill-scanner
Showing 25 of 124; the rest are in the per-scanner reports above.