github Python analyzed 4a77849 deep scan · partial (375/2,309 files)

brcampidelli/chimera-agent

Open-source AI agent that reasons by blending many AI models, does real work on its own, and keeps learning — safe, self-hostable, and fully yours.

maintainer: brcampidelli
licence: Apache-2.0
first seen: 2026-07-02
last seen: 2026-09-10
releases · 30d: 66
short id

risk 64/100 · heuristic grade

D high inferred analyzer v33 (current)

capability exposure inferred + 35
recent drift inferred + 20
tool safety inferred + 12
trust mitigators mixed − 3

inferred mixed

The A–E grade is our heuristic synthesis — a "review this" prompt, not a verdict. Each factor is tagged by what backs it: attested (a verifiable record), reported (a third party's claim), or inferred (our own heuristic, e.g. permissions). See methodology.

grade last moved 3d ago · see ecosystem CVEs →

risk trajectory 6 movements

2w ago C · 56 → D · 64
3w ago C · 44 → C · 56
4w ago D · 64 → C · 44
5w ago C · 57 → D · 64
9w ago C · 48 → C · 57
9w ago C · 40 → C · 48

capability exposure grade factor +35

Inferred surface — each links to servers holding it:

vulnerabilities 0 CVEs

No known CVEs for this server.

tool safety 1 findings · grade factor +12

high dangerous code

committed secret: OpenAI key · dynamic exec: eval()/exec(), __import__ sink

skills & danger signals github-tarball

prompt-surface shipped agent-instruction files + hidden-content / dangerous-code findings — quoted from the analyzed source

analyzed commit 4a77849 · analyzer v33 · 5h ago

skills & prompt files 24

danger signals18

dynamic code execution eval()/exec() brcampidelli-chimera-agent-4a77849/chimera/tools/code.py :68 exec(compile(code, "<code_interpreter>", "exec"), self._namespace) # noqa: S102
dynamic code execution __import__ sink brcampidelli-chimera-agent-4a77849/tests/test_settings_from_the_environment.py :115 "PATH": __import__("os").environ.get("PATH", ""),
suspicious endpoint api.telegram.org brcampidelli-chimera-agent-4a77849/chimera/server/telegram_adapter.py :24 _API = "https://api.telegram.org"
suspicious endpoint discord.com expected for this server's purpose brcampidelli-chimera-agent-4a77849/tests/test_a_secret_must_not_become_a_durable_fact.py :37 ("o webhook é https://discord.com/api/webhooks/123/aBcDeF-gH1jKlMnOpQrStUvW",
suspicious endpoint 169.254.169.254 (cloud metadata) brcampidelli-chimera-agent-4a77849/tests/test_browser.py :226 out = tool.run(action="screenshot", url="http://169.254.169.254/latest/", path="shot.png")
suspicious endpoint discord.com expected for this server's purpose brcampidelli-chimera-agent-4a77849/tests/test_cron_delivery.py :78 assert payload_for("https://discord.com/api/webhooks/1/x", "oi") == {"content": "oi"}
suspicious endpoint 169.254.169.254 (cloud metadata) brcampidelli-chimera-agent-4a77849/tests/test_download.py :19 out = DownloadMediaTool(tmp_path).run(url="http://169.254.169.254/latest/meta-data/")
suspicious endpoint 169.254.169.254 (cloud metadata) brcampidelli-chimera-agent-4a77849/tests/test_native_tools.py :138 out = HttpGetTool().run(url="http://169.254.169.254/latest/meta-data/")
suspicious endpoint 169.254.169.254 (cloud metadata) brcampidelli-chimera-agent-4a77849/tests/test_ssrf.py :14 "http://169.254.169.254/latest/meta-data/", # cloud metadata
suspicious endpoint 8.8.8.8 brcampidelli-chimera-agent-4a77849/tests/test_ssrf.py :30 check_url("http://8.8.8.8/") # public IP, does not raise
suspicious endpoint 93.184.216.34 brcampidelli-chimera-agent-4a77849/tests/test_ssrf.py :31 assert is_safe_url("https://93.184.216.34/") is True # example.com's IP
suspicious endpoint discord.com expected for this server's purpose brcampidelli-chimera-agent-4a77849/tests/test_the_place_gives_the_secret_away.py :58 ("https://discord.com/api/webhooks/1234567890/aBcDeF-gH1jKlMnOpQrStUvW",
committed secret OpenAI key brcampidelli-chimera-agent-4a77849/chimera/governance/audit.py :92 sk-AAA…(23 chars, redacted)
committed secret OpenAI key brcampidelli-chimera-agent-4a77849/tests/test_a_secret_must_not_become_a_durable_fact.py :34 sk-pro…(30 chars, redacted)
committed secret OpenAI key brcampidelli-chimera-agent-4a77849/tests/test_api.py :1170 sk-sup…(23 chars, redacted)
committed secret OpenAI key brcampidelli-chimera-agent-4a77849/tests/test_nobody_read_the_wheel.py :39 sk-pro…(30 chars, redacted)
committed secret OpenAI key brcampidelli-chimera-agent-4a77849/tests/test_the_doctor_never_called_the_provider.py :99 sk-pro…(30 chars, redacted)
committed secret OpenAI key brcampidelli-chimera-agent-4a77849/tests/test_the_place_gives_the_secret_away.py :13 sk-pro…(30 chars, redacted)

other grade factors evidence elsewhere

recent drift +20 capability drift →

embed badge readme-ready

[![MCP Observatory risk grade](https://mcpobservatory.com/servers/github:brcampidelli/chimera-agent/badge.svg)](https://mcpobservatory.com/servers/github:brcampidelli/chimera-agent/security)

Heuristic, inferred signals — false positives (legitimately powerful tools, forks, language ports) are expected. Treat each as "review this", not a verdict. See the ecosystem-wide picture on the security hub, or the fleet security of brcampidelli.

brcampidelli/chimera-agent

skills & prompt files 24

danger signals18

Navigate

Stream

Features

Display