Skills/Glama/catalogo-fuentes-publicas

catalogo-fuentes-publicas@0.10.0

VERIFIED· install only

Publisher claims: "Enables AI agents and developers to search and inspect Spanish public data sources, learn their endpoints and pitfalls, and retrieve ready-made data such as municipal profiles, economic indicators, company records, procurement, subsidies, and location reports." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry GlamaPublisher bquantfinance · publishing for 3 daysInstalls 0Last detonated 3d ago
$npx skills add catalogo-fuentes-publicas
WatchReport an issue

Coverage

Nothing executable in the bundle ran; the trace covers the install step only.
Tested
every file read, file written and host contacted by what ran
Not tested
use of the skill by an agent

What this means for the label: Verified 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 gob.es, ine.es, boe.es, juntadeandalucia.es, gva.es, sigpac-hubcloud.es, contrataciondelestado.es, infosubvenciones.es, transparenciacatalunya.cat, comunidad.madrid, githubusercontent.com, aemet.es, arcgis.com, dgt.es, madrid.es, barcelona.cat, cnmc.es, renfe.com, mir.es, cartociudad.es, umn.edu, opengis.net, bde.es, purl.org, tesoro.es, fnmt.es, ign.es, x.es, publico.example, otro.example — 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
use of the skill by an agent

Connect it under the guard. Nothing executable in the bundle ran; the trace covers the install step only. 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 -- <the server's command>

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 (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-11 and scored it 83/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 1 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessscript backend runs setup only
0.0sprocessscript backend runs setup only
0.0sprocessno install scripts to re-run

Static findings

LOW
Prompt injectionindices/README.md:29 · Prompt injection — known jailbreak technique reference · informational: not an instruction file…ones paginadas, altas por fecha de alta) - frescura: diaria; las concesiones se dan de alta con meses de retraso (filtrar por fechaRegInicio, no por fecha de conce…Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
MEDIUM
Python subprocess execution detectedscripts/ronda_residencial.py:62 · Python subprocess execution detectedp = subprocess.run([sys.executable, *args], cwd=RAIZ, capture_output=True, text=True, timeout=limite,Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/check_cifras.py:64 · Python subprocess execution detectedp = subprocess.run([sys.executable, str(Path(__file__).resolve()), "--hijo"], input=codigo, text=True,Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
CRITICAL
Prompt injectionplugins/fuentes-publicas/skills/fuentes-publicas/SKILL.md:16 · Prompt injection — known jailbreak technique reference2. Lee primero `alerts` de la ficha: trampas silenciosas que dan una cifra incompleta o distinta sin error. Aplica laFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
MEDIUM
Access to sensitive file pathsscripts/test_clientes.py:328 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesalmacen.sql("select * from read_csv('/etc/passwd')", d)Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
README links to an external installerindices/README.md → https://contrataciondelestado.es/sindicacion/sindicacion_643/licitacionesPerfilesContratanteCompleto3_202508.ziphttps://contrataciondelestado.es/sindicacion/sindicacion_643/licitacionesPerfilesContratanteCompleto3_202508.zipFix: Pin versions and sources; vendor anything fetched at install time.
AST06
LOW
Prompt injectionindices/README.md:1032 · Prompt injection — known jailbreak technique reference · informational: not an instruction file- vía `ine-cartografia-censal`: CNUT0 a CNUT3 por sección; concatenados dan el NUTS3 (ES + 2 + 1 + 1 = ES211)Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
MEDIUM
URL to the cloud instance metadata addressscripts/test_clientes.py:478 · URL to the cloud instance metadata address — reads the VM's credentialssaltos = {"https://publico.example/a": "http://169.254.169.254/latest/meta-data/",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07
MEDIUM
Python subprocess execution detectedscripts/check_ejemplos.py:135 · Python subprocess execution detectedp = subprocess.run(cmd + args, capture_output=True, text=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
LOW
Prompt injectionsources/vivienda-urbanismo/README.md:8 · Prompt injection — known jailbreak technique reference · informational: not an instruction file…y Comunitat Valenciana más el INE (VTE) en todos los municipios; registro e INE dan cifras distintas (Madrid 4.865 inscritas y 10.836 anunciadas); perfil_municipio…Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Prompt injectionindices/README.md:949 · Prompt injection — known jailbreak technique reference · informational: not an instruction file…y Comunitat Valenciana más el INE (VTE) en todos los municipios; registro e INE dan cifras distintas (Madrid 4.865 inscritas y 10.836 anunciadas); perfil_municipio…Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Prompt injectionindices/README.md:280 · Prompt injection — known jailbreak technique reference · informational: not an instruction file…AAAAMMDD) para detectar normas modificadas; datos-auxiliares/rangos y /materias dan los códigos de filtro ``` curl -s -H "Accept: application/json" "https://…Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Prompt injectionREADME.md:63 · Prompt injection — known jailbreak technique reference · informational: not an instruction file…as, límites no documentados, URLs que cambian. Las trampas silenciosas, las que dan una cifra incompleta o distinta sin ningún error, van aparte en `alerts`, y el …Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Prompt injectionindices/README.md:190 · Prompt injection — known jailbreak technique reference · informational: not an instruction file2. `ine-api-tempus`: DATOS_TABLA/{Id}?nult=4&tip=A devuelve todas las series de la tabla; para filtrar, VARIABLES_OPERACION y VALORES_VARIABLEOPERACION dan los pares tv=id_variable:id_valorFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01

Cost to the agent

Instructions loaded
≈1,211 tok
1 file · 79 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.