timesfm-forecasting

SAFE max severity LOWSkillSpector Do not install 73 registry K-Dense-AI last scanned 2026-10-21 1 scan

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

Findings2

Critical0

High0

Medium0

Low2

Analyzersstatic bytecode pipeline correlation behavioral trigger

Scanner version2.3.1

Second scanner: NVIDIA SkillSpector

VerdictDo not install 73

Score73 / 100

Issues5

CategoriesDangerous Code Execution MCP Least Privilege Tool Misuse

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

Performs zero-shot time-series forecasting with Google's TimesFM, including regular-grid CSV preparation, quantile forecasts, XReg covariates, and held-out evaluation. Uses the Apache-licensed TimesFM 2.5 checkpoint by default and documents the distinct TimesFM 3.0 multivariate API and weight-license requirements.

Package: 21 files, 140 KB
SKILL.md: 1027 words, 9 sections
Code: Python (9), Shell (1)
Allowed tools: Read Write Edit Bash
License: Apache-2.0 license
Compatibility: Requires Python 3.10+ and timesfm 3.0.2 with PyTorch; CSV tooling also needs NumPy and pandas. Network access and cache space are needed for initial Hugging Face checkpoint download. Optional XReg needs JAX and scikit-learn; current JAX requires Python 3.12+.

SKILL.md covers: TimesFM Forecasting · Choose the model/API first · Workflow · Installation · TimesFM 2.5 quick start · 2.5 may append dummy series to its input list during batching; pass a fresh list. · CSV helper · Covariates and anomaly screening · References and examples

Findings

LOW Code uses search/grep patterns but Grep tool not in allowed-tools Unauthorized Tool Usestatic

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

SKILL.md

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

LOW Script contacts a destination the documentation never mentions Unauthorized Tool Usestatic

Script contacts or configures 'cdn.jsdelivr.net' but the skill documentation never visibly mentions it. Undocumented network destinations can indicate behaviour the manifest and description do not disclose.

examples/global-temperature/generate_html.py:26

Remediation: Document the destination in SKILL.md (or the manifest description) if it is intended, or remove the undisclosed network access. Organizations can list internal hosts in llm_analysis.trusted_reference_domains.

What is in the package

21 files, 140 KB. Show the list.

File	Kind	Size
`SKILL.md`	doc	9.3 KB
`references/api_reference.md`	doc	6.1 KB
`references/data_preparation.md`	doc	3.4 KB
`references/examples_and_validation.md`	doc	3.1 KB
`references/output_and_config.md`	doc	2.3 KB
`references/performance_tuning.md`	doc	1.7 KB
`references/system_requirements.md`	doc	3.1 KB
`references/timesfm3.md`	doc	4.2 KB
`references/workflows.md`	doc	2.7 KB
`scripts/check_system.py`	script	16 KB
`scripts/forecast_csv.py`	script	11 KB
`examples/anomaly-detection/detect_anomalies.py`	script	18 KB
`examples/covariates-forecasting/demo_covariates.py`	script	19 KB
`examples/global-temperature/README.md`	doc	1.7 KB
`examples/global-temperature/generate_animation_data.py`	script	2.6 KB
`examples/global-temperature/generate_gif.py`	script	7.2 KB
`examples/global-temperature/generate_html.py`	script	21 KB
`examples/global-temperature/run_example.sh`	script	435 B
`examples/global-temperature/run_forecast.py`	script	2.6 KB
`examples/global-temperature/temperature_anomaly.csv`	data	591 B
`examples/global-temperature/visualize_forecast.py`	script	3.8 KB

External hosts referenced

github.com huggingface.co pypi.org cdn.jsdelivr.net docs.pytorch.org pytorch.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

OUTPUT_DIR HF_HUB_CACHE HF_HOME XDG_CACHE_HOME

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

Static analyzer. Pattern rules over SKILL.md and bundled files: known-bad commands, exfiltration URLs, secrets, obfuscation.
Bytecode analyzer.
Pipeline analyzer.
Correlation analyzer.
Behavioral analyzer. Checks what the skill asks the agent to do against what its description claims it does.
Trigger analyzer. Looks for instructions that fire on conditions the user did not ask for.

What we did not check

Runtime behaviour. The skill was not executed; findings come from reading its files.
Anything fetched at install or run time, including remote scripts, package dependencies, and URLs the skill tells the agent to open.
Content the analyzers cannot read: images, binaries, and some non-English text.
Known scanner bypass classes. See the methodology and limitations page.

Sources

Repository: https://github.com/K-Dense-AI/scientific-agent-skills
Raw scan result: skills-timesfm-forecasting-scan.json
Badge for your README: ![skillscan.io](https://skillscan.io/badge/k-dense-ai-timesfm-forecasting.svg)
Request a re-scan