Skills/PyPI/gemini-faf-mcp

gemini-faf-mcp@3.3.0

CAUTION· not started

Publisher claims: "Persistent Project Context for Google Gemini. IANA-registered .faf format, MCP server + Cloud Run REST API, unifies CLAUDE.md, GEMINI.md, AGENTS.md." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher wolfe-jam · publishing for 287 daysInstalls 1,202Last detonated 9 h ago
What would fix thisWatchDispute verdict

Coverage

Not started: dependency install failed; the server itself was not observed.
Tested
the dependency install step · every file read, file written and host contacted by what ran
Not tested
server startup · the tool list · tool behavior

What this means for the label: Caution here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.

Before you give it your token

It will ask for
no credential variables read in the code
Where it talks to
no vendor host named in the codeAlso faf.one, run.app — not the publisher's domain; check what for before connecting.
What the honeypot saw
no credential files read · no network
What we could not test
server startup · the tool list · tool behavior

Connect it under the guard. Not started: dependency install failed; the server itself was not observed. The code names no credential variable; the guard pins the network to what the honeypot saw and logs every call.

$vet-skills run --net declared -- uvx gemini-faf-mcp

Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; not started: dependency install failed; the server itself was not observed) on 2026-11-14 and scored it 73/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Hidden zero-width characters detected; Access to sensitive file paths; Access to sensitive file paths. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.1sprocessdependency install exit 1 ·
0.1sclaimednot started: dependency install failed (exit 1); the server itself was not observed
0.1sprocessscript backend runs setup only
0.1sprocessno install scripts to re-run

Static findings

HIGH
Hidden zero-width characters detectedinject.py:136 · Hidden zero-width characters detected — may conceal contentif existing.lstrip("").lstrip().startswith(FAF_METASTAMP) or _has_unpaired_marker(existing, start, end):Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST07
HIGH
Access to sensitive file pathssafe_path.py:12 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files`.faf` / `.fafm` context file. Blocks /etc/passwd, ~/.ssh/id_rsa,Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Access to sensitive file pathstests/test_wjttc_mk4.py:469 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"path": "../../../etc/passwd"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Unicode escape sequence detectedtests/test_wjttc_mk4.py:383 · Unicode escape sequence detected — may contain obfuscated payloadsassert "\u30d7\u30ed\u30b8\u30a7\u30af\u30c8" in contentFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
MEDIUM
Access to sensitive file pathstests/test_security_path_confinement.py:87 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesassert not is_faf_context_file(Path("/etc/passwd"))Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Hex-encoded string detectedtests/test_wjttc_mk4.py:337 · Hex-encoded string detected — may contain obfuscated payloadsbinary.write_bytes(b"\x00\x01\x02\xff\xfe\xfd")Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
MEDIUM
Python subprocess execution detectedtests/test_extension_launch.py:47 · Python subprocess execution detectedflags = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Access to sensitive file pathstests/test_security_path_confinement.py:94 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesresult = await _call_error(client, "faf_read", {"path": "/etc/passwd"})Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathssafe_path.py:13 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files~/.aws/credentials, .env, etc. regardless of directory.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Python subprocess execution detectedtests/test_no_symlinks.py:22 · Python subprocess execution detectedout = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
References a credential file in the home directorysafe_path.py:12 · References a credential file in the home directory`.faf` / `.fafm` context file. Blocks /etc/passwd, ~/.ssh/id_rsa,Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST03
MEDIUM
Python subprocess execution detectedtests/test_cli_flags.py:23 · Python subprocess execution detectedreturn subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
References a credential file in the home directorysafe_path.py:13 · References a credential file in the home directory~/.aws/credentials, .env, etc. regardless of directory.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST03
MEDIUM
Python subprocess execution detectedtests/test_extension_launch.py:40 · Python subprocess execution detectedout = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Hidden zero-width characters detectedinject.py:250 · Hidden zero-width characters detected — may conceal contentbom = "" if existing.startswith("") else ""Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST07
MEDIUM
Access to sensitive file pathstests/test_security_path_confinement.py:62 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesconfine_path("../../../../../../etc/passwd")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Unicode escape sequence detectedtests/test_wjttc_mk4.py:379 · Unicode escape sequence detected — may contain obfuscated payloads"name": "\u30d7\u30ed\u30b8\u30a7\u30af\u30c8", "path": targetFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
MEDIUM
Access to sensitive file pathstests/test_security_path_confinement.py:58 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesconfine_path("/etc/passwd")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
LOW
Instructs the agent to modify its persistent memory or instruction filesserver.py:394 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file"""Export and write AGENTS.md from a .faf file (non-destructive).Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Instructs the agent to modify its persistent memory or instruction filesgemini_faf_mcp.egg-info/PKG-INFO:115 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file**faf_gemini and faf_agents keep your hand-written GEMINI.md and AGENTS.md, and tell you what they couldn't write.**Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Instructs the agent to modify its persistent memory or instruction filesREADME.md:73 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file**faf_gemini and faf_agents keep your hand-written GEMINI.md and AGENTS.md, and tell you what they couldn't write.**Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Instructs the agent to modify its persistent memory or instruction filesPKG-INFO:115 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file**faf_gemini and faf_agents keep your hand-written GEMINI.md and AGENTS.md, and tell you what they couldn't write.**Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Instructs the agent to modify its persistent memory or instruction filesserver.py:80 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file"project.faf is the source: faf_gemini and faf_agents write GEMINI.md and AGENTS.md from it, leaving hand-written content alone.",Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01

Cost to the agent

Instructions loaded
≈74 tok
1 file · 36 in bundle
Tool list per prompt
≈0 tok
0 tools · 0 per tool
Handshake
no reply
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 0

Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.

Known vulnerabilities

No advisories in OSV for gemini-faf-mcp@3.3.0 as of 8 h ago. This is the package itself, not its dependencies.

What would make this Verified

7 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim wolfe-jam: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Hidden zero-width characters detected≈ +4 on the totalKeep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
  3. Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  4. References a credential file in the home directory≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  5. Unicode escape sequence detected≈ +2 on the totalPut hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
  6. Hex-encoded string detected≈ +2 on the totalPut hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
Publish a new version to PyPI, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim wolfe-jamPropose a patch to the maintainer