hephaestus-storm
Use when the user types /hep-storm, says @Hephaestus storm <goal>, or asks to drive a goal to verified completion through a force-robust Stormbreaker loop. Stormbreaker routes the goal to real Agentlas specialists, materializes a dependency-ordered pipeline fabric, and runs each work packet as a verifier-first hardened loop that does not stall, run away, or claim false success. Use it for loop-worthy work — apps, sites, agents, automations, debugging, multi-step research, data/report generation. Trivial questions are answered directly, not stormed.
68
83%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Critical
Do not install without reviewing
Security
1 critical severity finding. Installing this skill is not recommended: please review these findings carefully if you do intend to do so.
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
This is a direct curl of a raw GitHub-hosted shell installer (curl ... | bash) from a non-official/third‑party repo — an unvetted .sh installer can execute arbitrary code and is a high-risk distribution vector.
Low
Low-risk findings.
2 low severity findings. Worth noting, but not necessarily harmful.
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 runtime workflow drives outsider-authored free text into the Stormbreaker engine by passing “<the user's goal>” (i.e., user-provided text from the chat/command) directly to `"$RUNNER" hep-storm "<the user's goal>"` without pre-selecting any specific item.
W012: Unverifiable external dependency detected (runtime URL that controls agent).
What this means
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
Why it was flagged
The skill instructs at runtime to run a one‑touch installer that fetches and pipes remote code to a shell (curl -fsSL https://raw.githubusercontent.com/agentlas-ai/Agentlas-OS/main/scripts/install-all-runtimes.sh | bash), which executes external code and is presented as a required fallback when no local runner exists.
- Repository
- agentlas-ai/Agentlas-OS
- Commit
2eb39ad
- Audited
- Security analysis
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.