CtrlK
BlogDocsLog inGet started
Tessl Logo

fractal

Delegate analysis- and context-heavy work to Fractal, an agentic CLI powered by a self-harnessed Recursive Language Model (predict-rlm), by running it non-interactively (fractal -p). Reach for it when a task needs reasoning over a large or deep codebase, synthesizing an answer across many files, auditing, or open-ended investigation — work that would otherwise flood your own context. The RLM reasons over context programmatically (no context rot) and returns a distilled answer. Use when asked to run Fractal headless, script it, call it from CI or another agent, or offload a heavy analysis/large-context task. Less suited to trivial single-file edits you can do directly.

76

Quality

96%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Critical

Do not install without reviewing

SKILL.md
Quality
Evals
Security

Security

1 critical severity finding. Installing this skill is not recommended: please review these findings carefully if you do intend to do so.

Critical

E005: Suspicious download URL detected in skill instructions.

What this means

Detected a suspicious URL in the skill instructions that could lead the agent to download and execute malicious scripts or binaries. This includes links to executables from untrusted sources, typosquatting of official packages, URL shorteners that obscure the destination, and personal file hosting services.

Why it was flagged

The curl | sh installer at https://fractal.trampoline.ai/install.sh is high-risk because it downloads and executes an arbitrary shell script from a non-standard host (a direct remote install script), while the GitHub and docs links are just references and not direct downloads.

Report incorrect finding

Low

Low-risk findings.

1 low severity finding. Worth noting, but not necessarily harmful.

Low

W011: Third-party content exposure detected (indirect prompt injection risk).

What this means

The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.

Why it was flagged

The required runtime workflow ingests outsider-authored free text via the headless prompt argument/stdin (`fractal -p "<task>"` / `-p -`), which is supplied by the user of the CLI and then used by the agent inside its Docker sandbox.

Repository
jasonkneen/tiny-world-builder
Audited
Security analysis
Snyk

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.