Loading the registry…
AnkaLoop is an out-of-the-box coding-agent runtime for terminal, server, and Telegram, with built-in tools, subagents, skills, memory, MCP, hooks, and automation.
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.
1 critical finding reported by agent-audit-kit. The composite score alone does not reflect this — read the per-scanner reports below.
This artifact ships from 3 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/tao12345666333/ankaloop, 153 findings
Choose your runtime: the CLI writes the mcpServers config entry for that target.
nerlo install --target claude-code -- ankaloop
Install respects the composite badge: Clean proceeds, Caution prompts for confirmation, and Flagged is refused. Write operations require an API token.
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
104 findings · 14.5s
v0.3.74
27 findings · 20.3s
v0.1.0
6 findings · 8.8s
v0.1.0
4 findings · 8.8s
v0.1.0
0 findings · 32.9s
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 141 findings across every scanner that examined this package. None of the 1 finding rated critical by their scanner were dismissed.
Not reviewed is not the same as clean. Those 4 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.
39 Documentation or example — The match is in documentation or sample code, confirmed by our own check to be outside the installed artifact.
Rules: MANIFEST_MISSING_LICENSE, SOCIAL_ENG_VAGUE_DESCRIPTION, MANIFEST_INVALID_NAME and 1 more · Files: /repo/examples/plugins/security-guidance/skills/security-best-practices/SKILL.md, /repo/examples/skills/code-review/SKILL.md, /repo/examples/skills/python-expert/SKILL.md and 20 more · reported by cisco-skill-scanner, nerlo-install-instruction
8 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/ci.yml, .github/workflows/release.yml, .github/workflows/docker-image.yml · reported by agent-audit-kit
1 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: TOOL_ABUSE_UNDECLARED_NETWORK · Files: /repo/repo/AGENTS.md · reported by cisco-skill-scanner
1 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-TASKS-004 · Files: tests/test_execution_boundaries.py · 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.
16 MANIFEST_MISSING_LICENSE
Files: /repo/src/ankaloop/builtin_skills/session-cleanup/SKILL.md, /repo/src/ankaloop/builtin_skills/skill-creator/SKILL.md, /repo/src/ankaloop/builtin_skills/telegram-sender/SKILL.md and 13 more · reported by cisco-skill-scanner
14 DATA_EXFIL_NETWORK_REQUESTS
Files: /repo/src/ankaloop/builtin_skills/telegram-sender/scripts/telegram_send.py, /repo/scripts/e2e_serve_skill_selftest.py, /repo/src/ankaloop/telegram/tools.py and 1 more · reported by cisco-skill-scanner
12 RESOURCE_ABUSE_INFINITE_LOOP
Files: /repo/src/ankaloop/client/ws_client.py, /repo/src/ankaloop/init_wizard.py, /repo/src/ankaloop/mcp_naming.py and 2 more · reported by cisco-skill-scanner
8 SOCIAL_ENG_VAGUE_DESCRIPTION
Files: /repo/SKILL.md, /repo/deploy-vm/SKILL.md, /repo/deploy-k8s/SKILL.md and 5 more · reported by cisco-skill-scanner
7 HIDDEN_DATA_FILE
Files: /repo/.agent/workflows/skills-and-commands.md, /repo/.amcp/skills/gh-ci-analyzer/references/gh-cli-cheatsheet.md, /repo/.amcp/skills/gh-pr-review/SKILL.md and 4 more · reported by cisco-skill-scanner
4 opt.nerlo-rules.nerlo-py-secret-to-network-egress
Files: /repo/src/ankaloop/builtin_skills/telegram-sender/scripts/telegram_send.py · reported by nerlo-behavioral
3 AAK-SECRET-004
Files: deploy-k8s/secret.example.yaml, src/ankaloop/telegram/config.py · reported by agent-audit-kit
3 HIDDEN_EXECUTABLE_SCRIPT
Files: /repo/.amcp/skills/gh-ci-analyzer/scripts/analyze-failed-run.sh, /repo/.amcp/skills/gh-ci-analyzer/scripts/generate-report.sh, /repo/.amcp/skills/gh-ci-analyzer/scripts/batch-analyze.sh · reported by cisco-skill-scanner
2 AAK-TASKS-003
Files: src/ankaloop/__init__.py, src/ankaloop/tool_execution.py · reported by agent-audit-kit
2 AAK-TASKS-004
Files: src/ankaloop/agent.py, src/ankaloop/tool_execution.py · reported by agent-audit-kit
2 opt.nerlo-rules.nerlo-py-dynamic-exec
Files: /repo/src/ankaloop/commands.py, /repo/src/ankaloop/tools.py · reported by nerlo-behavioral
1 AAK-ANTHROPIC-SDK-001
Files: src/ankaloop/mcp_client.py · reported by agent-audit-kit
1 AAK-MCP-NOAUTH-DEFAULT
Files: src/ankaloop/init_wizard.py · reported by agent-audit-kit
1 AAK-MCP-SDK-CVE-2026-52869-001
Files: uv.lock · reported by agent-audit-kit
1 AAK-MCP-STATELESS-004
Files: src/ankaloop/client/__init__.py · reported by agent-audit-kit
1 AAK-OAUTH-008
Files: src/ankaloop/server/app.py · reported by agent-audit-kit
1 AAK-SEC-MD-001
Files: SECURITY.md · reported by agent-audit-kit
1 AAK-SKILL-UNTRUSTED-EXEC-PATH
Files: deploy-vm/install-vm.sh · reported by agent-audit-kit
1 AAK-TASKS-001
Files: src/ankaloop/task.py · reported by agent-audit-kit
1 EXCESSIVE_FILE_COUNT
Files: /repo/. · reported by cisco-skill-scanner
1 LOW_ANALYZABILITY
Files: /repo/.amcp/skills/gh-pr-review · reported by cisco-skill-scanner
1 opt.nerlo-rules.nerlo-install-pipe-to-shell
Files: /repo/deploy-vm/install-vm.sh · reported by nerlo-install-instruction
1 opt.nerlo-rules.nerlo-install-run-bundled-artifact
Files: /repo/deploy-k8s/README.md · reported by nerlo-install-instruction
1 opt.nerlo-rules.nerlo-install-shell-inline-command
Files: /repo/.amcp/skills/gh-ci-analyzer/references/common-failure-patterns.md · reported by nerlo-install-instruction
1 TOOL_ABUSE_UNDECLARED_NETWORK
Files: /repo/src/ankaloop/builtin_skills/telegram-sender/repo/src/ankaloop/builtin_skills/telegram-sender/SKILL.md · reported by cisco-skill-scanner
The model could have called any of these a false positive and did not.
1 AAK-MCP-ENV-PLACEHOLDER-EXFIL-001
Files: src/ankaloop/mcp_client.py · reported by agent-audit-kit
4 The model did not answer for these findings.
Rules: FILE_MAGIC_MISMATCH, AAK-TASKS-003 · Files: /repo/examples/commands/explain.toml, tests/test_task.py, tests/test_execution_boundaries.py · reported by cisco-skill-scanner, agent-audit-kit
Critical risks from credential exfiltration and shell execution
The artifact contains a critical finding related to environment variable placeholder exfiltration in `src/ankaloop/mcp_client.py`. It also includes high-severity findings for potential credential access in `deploy-k8s/secret.example.yaml` and `src/ankaloop/telegram/config.py`, and network egress of secrets from `src/ankaloop/builtin_skills/telegram-sender/scripts/telegram_send.py`. Additionally, hidden executable scripts are present in `/repo/.amcp/skills/gh-ci-analyzer/scripts/`, and multiple files contain code that could lead to resource abuse via infinite loops.
Concern level assessed by the review: Critical. This is the review's scale, not the registry badge.
Showing 25 of 31; the rest are in the per-scanner reports above.
Reviewed by gemini-2.5-flash. The model sees the findings, not your code, and cannot change a score.