protocolsio-integration

SAFE max severity MEDIUMSkillSpector Do not install 100 registry K-Dense-AI last scanned 1 scan

Verdict safe, but 3 findings (2 medium, 1 low), mainly unauthorized tool use, data exfiltration. Most recent scan 2026-10-21.

Findings3
Critical0
High0
Medium2
Low1
Analyzersstatic bytecode pipeline correlation behavioral trigger
Scanner version2.3.1

Second scanner: NVIDIA SkillSpector

VerdictDo not install 100
Score100 / 100
Issues24
CategoriesTool Misuse Privilege Escalation MCP Least Privilege
Version2.12.0 (static)

The two scanners disagree: Cisco found nothing and SkillSpector says do not install. One of them has a blind spot here; read the skill before trusting either. How the two scanners compare across the whole corpus: Two scanners, one corpus.

What this skill does

Reads, validates, and safely exports protocols.io data with current official REST/MCP contracts, or creates non-executing mutation plans. The bundled client makes bounded official-host GET requests only with explicit --execute. Use only for tasks explicitly targeting protocols.io or an exact protocols.io protocol version.

Package
15 files, 151 KB
SKILL.md
1587 words, 12+ sections
Code
Python (7)
Allowed tools
Read Write Python
License
MIT
Compatibility
Bundled CLIs require Python 3.11+ and use only the standard library. Offline validation and planning need no credentials or network. REST reads require HTTPS access to official protocols.io hosts and usually a named bearer token; network access is disabled unless --execute is supplied. The scripts never load .env files or execute mutations.

SKILL.md covers: protocols.io Integration · Operating Contract · Current API Map · Authentication and Access · Safe Read Workflow · Pagination · Offline Protocol Validation · Mutation and Upload Workflow · Errors and Rate Limits · Official Integrations · References · Citing Scientific Agent Skills

Findings

MEDIUM Code makes network requests Unauthorized Tool Usestatic

Skill code makes network requests. While not controlled by allowed-tools, network access should be documented and justified in the skill description.

SKILL.md

Remediation: Document network usage in skill description or remove network operations if not needed
MEDIUM Outbound network request primitives that can transmit data externally Data Exfiltrationstatic

Pattern detected: urllib.request.Request(

scripts/_common.py:557

request = urllib.request.Request(
Remediation: Ensure network operations are necessary and document allowed destinations
LOW Code uses search/grep patterns but Grep tool not in allowed-tools Unauthorized Tool Usestatic

Skill restricts tools to ['Read', 'Write', 'Python'] but code uses regex search patterns

SKILL.md

Remediation: Add 'Grep' to allowed-tools or remove regex search operations

What is in the package

FileKindSize
SKILL.mddoc13 KB
assets/protocol-snapshot.schema.jsonconfig4.2 KB
references/additional_features.mddoc9.8 KB
references/authentication.mddoc6.4 KB
references/discussions.mddoc6.4 KB
references/file_manager.mddoc10 KB
references/protocols_api.mddoc11 KB
references/workspaces.mddoc8.1 KB
scripts/__init__.pyscript76 B
scripts/_common.pyscript20 KB
scripts/pagination_helper.pyscript7.5 KB
scripts/plan_write_request.pyscript23 KB
scripts/protocols_read.pyscript16 KB
scripts/validate_auth_config.pyscript3.4 KB
scripts/validate_protocol_json.pyscript12 KB

External hosts referenced

www.protocols.io apidoc.protocols.io arxiv.org protocols.io tenant.protocols.io doi.org export.arxiv.org json-schema.org

Hostnames that appear in the skill's files. Referencing a host is not a finding; compare against the findings above and the skill's stated purpose.

Environment variables referenced

PROTOCOLS_IO_ACCESS_TOKEN

Package contents recorded 2026-10-22 at commit 593377bb0487. The scan above ran against the version current at scan time; the two can differ if the skill has since been updated.

What we checked

What we did not check

Sources

Related skills