Loading the registry…
Production-oriented AI agent security middleware prototype.
Cursor Rules are .cursorrules / .cursor/rules files that steer Cursor's AI; 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.
11 critical findings reported by cisco-skill-scanner. 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/lakshyakgupta/agentshield, 347 findings
Cursor Rules are .cursorrules / .cursor/rules files that steer Cursor's AI. Review the scanned source before copying them into your own project.
nerlo install -- agentshield
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.
v2.0.11
248 findings · 18.4s
v0.3.74
35 findings · 11.2s
v0.1.0
26 findings · 16.0s
v0.1.0
0 findings · 16.0s
v0.1.0
0 findings · 15.4s
v1.4.0
None of the entry points this scanner reads were found in this artifact. What each scanner covers
0 findings · 0.2s
vv0.3.2
No Go packages were found in this artifact. What each scanner covers
0 findings · 0.1s
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 ·n/a: not applicablecisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completecapslock ·n/a: not applicablenerlo-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 309 findings across every scanner that examined this package. None of the 11 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.
12 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-py-secret-to-network-egress, DATA_EXFIL_NETWORK_REQUESTS, SOCIAL_ENG_VAGUE_DESCRIPTION and 2 more · Files: /repo/examples/langchain_agent.py, /repo/.github/SKILL.md, /repo/docs/SKILL.md · reported by nerlo-behavioral, cisco-skill-scanner
9 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-SPLUNK-TOKLOG-001, AAK-IPI-WILD-CORPUS-001, SECRET_CONNECTION_STRING and 2 more · Files: tests/e2e/verify_swagger.spec.ts, frontend/tests/e2e/verify_swagger.spec.ts, tests/test_integration_postgres.py and 4 more · reported by agent-audit-kit, cisco-skill-scanner
3 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-005, TOOL_ABUSE_UNDECLARED_NETWORK · Files: AGENTS.md, CLAUDE.md, /repo/repo/AGENTS.md · reported by agent-audit-kit, cisco-skill-scanner
3 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/release-sdk.yml, .github/workflows/ci.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.
67 FILE_MAGIC_MISMATCH
Files: /repo/archive/audits/agentshield-ledger-final.md, /repo/archive/audits/agentshield-chat-browser-after.md, /repo/archive/audits/agentshield-dashboard-after-sim.md and 31 more · reported by cisco-skill-scanner
49 HIDDEN_DATA_FILE
Files: /repo/archive/screenshots/.codex-visual-protect-refactor.png, /repo/archive/screenshots/.codex-visual-mobile-refactor-final.png, /repo/archive/screenshots/.codex-visual-evidence-refactor-final.png and 41 more · reported by cisco-skill-scanner
32 DATA_EXFIL_NETWORK_REQUESTS
Files: /repo/scripts/chat_with_gemini_agent.py, /repo/scripts/demo.py, /repo/scripts/run_shielded_agent.py and 4 more · reported by cisco-skill-scanner
21 opt.nerlo-rules.nerlo-py-secret-to-network-egress
Files: /repo/backend/app/main.py, /repo/backend/app/security/firebase_auth.py, /repo/backend/app/security/sandbox.py and 5 more · reported by nerlo-behavioral
14 SECRET_PASSWORD_VAR
Files: /repo/frontend/src/main.tsx, /repo/scripts/run_shielded_agent.py, /repo/scripts/chat_with_gemini_agent.py and 1 more
Artifact has critical prompt injection and credential harvesting risks
The artifact contains critical findings related to prompt injection and credential harvesting, indicating potential for unauthorized data access or manipulation. High severity findings show secrets being sent over the network and other prompt injection indicators. These issues are present in core application files, including those handling security and services.
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.
10 ARCHIVE_FILE_DETECTED
Files: /repo/archive/documentation_pack/AgentShield_Production_Documentation_Pack/docx/AgentShield_Security_Threat_Model.docx, /repo/archive/documentation_pack/AgentShield_Production_Documentation_Pack/docx/AgentShield_Implementation_Runbook.docx, /repo/archive/documentation_pack/AgentShield_Production_Documentation_Pack/docx/AgentShield_Test_and_Acceptance_Plan.docx and 2 more · reported by cisco-skill-scanner
10 MANIFEST_MISSING_LICENSE
Files: /repo/SKILL.md, /repo/.junie/SKILL.md, /repo/ai-system/SKILL.md and 7 more · reported by cisco-skill-scanner
10 SOCIAL_ENG_VAGUE_DESCRIPTION
Files: /repo/SKILL.md, /repo/.junie/SKILL.md, /repo/ai-system/SKILL.md and 7 more · reported by cisco-skill-scanner
10 UNANALYZABLE_BINARY
Files: /repo/archive/documentation_pack/AgentShield_Production_Documentation_Pack/docx/AgentShield_Test_and_Acceptance_Plan.docx, /repo/archive/documentation_pack/AgentShield_Production_Documentation_Pack/docx/AgentShield_Implementation_Runbook.docx, /repo/archive/documentation_pack/AgentShield_Production_Documentation_Pack/docx/AgentShield_Master_Production_Plan.docx and 2 more · reported by cisco-skill-scanner
9 AAK-SECRET-004
Files: scripts/chat_with_gemini_agent.py, scripts/run_shielded_agent.py, scripts/external_demo_agent.py and 4 more · reported by agent-audit-kit
9 YARA_prompt_injection_generic
Files: /repo/archive/audits/agentshield-agent-created-snapshot.md, /repo/archive/audits/agentshield-agents-empty-snapshot.md, /repo/archive/audits/agentshield-behavior-preruntime.md and 2 more · reported by cisco-skill-scanner
7 PROMPT_INJECTION_IGNORE_INSTRUCTIONS
Files: /repo/archive/audits/SKILL.md, /repo/archive/documentation_pack/AgentShield_Production_Documentation_Pack/sources/SKILL.md · reported by cisco-skill-scanner
6 AAK-IPI-WILD-CORPUS-001
Files: backend/openapi.json, backend/app/main.py, backend/app/services.py and 3 more · reported by agent-audit-kit
6 DATA_EXFIL_JS_NETWORK
Files: /repo/frontend/src/api.ts, /repo/frontend/src/main.tsx, /repo/sdk/nodejs/src/index.ts · reported by cisco-skill-scanner
3 opt.nerlo-rules.nerlo-js-secret-to-network-egress
Files: /repo/frontend/src/api.ts, /repo/frontend/src/main.tsx, /repo/sdk/nodejs/src/index.ts · reported by nerlo-behavioral
2 AAK-OAUTH-008
Files: backend/openapi.json, backend/app/main.py · reported by agent-audit-kit
2 AAK-SPLUNK-TOKLOG-001
Files: scripts/chat_with_gemini_agent.py, scripts/run_shielded_agent.py · reported by agent-audit-kit
2 EXCESSIVE_FILE_COUNT
Files: /repo/., /repo/archive/documentation_pack/AgentShield_Production_Documentation_Pack/. · reported by cisco-skill-scanner
2 MANIFEST_INVALID_NAME
Files: /repo/archive/documentation_pack/AgentShield_Production_Documentation_Pack/SKILL.md, /repo/.junie/SKILL.md · reported by cisco-skill-scanner
2 YARA_credential_harvesting_generic
Files: /repo/archive/audits/agentshield-attack-after-select-data.md · reported by cisco-skill-scanner
1 AAK-HEALTHCARE-AI-004
Files: HANDOFF.md · reported by agent-audit-kit
1 AAK-LEGAL-002
Files: frontend/package.json · reported by agent-audit-kit
1 AAK-OAUTH-001
Files: backend/app/main.py · reported by agent-audit-kit
1 AAK-OAUTH-005
Files: backend/app/main.py · reported by agent-audit-kit
1 AAK-OAUTH-006
Files: backend/app/main.py · reported by agent-audit-kit
1 AAK-OAUTH-007
Files: backend/app/main.py · reported by agent-audit-kit
1 LOW_ANALYZABILITY
Files: /repo/sdk/nodejs · reported by cisco-skill-scanner
1 RESOURCE_ABUSE_INFINITE_LOOP
Files: /repo/backend/app/main.py · reported by cisco-skill-scanner
1 TOOL_ABUSE_UNDECLARED_NETWORK
Files: /repo/sdk/python/repo/sdk/python/README.md · reported by cisco-skill-scanner
Showing 25 of 61; the rest are in the per-scanner reports above.