Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
swamp
v0.2.0Model any API with Swamp, test it, and enrich *Claw with new capabilities — full lifecycle from idea to working integration
⭐ 0· 560·0 current·0 all-time
byMagistr@umag
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Suspicious
medium confidencePurpose & Capability
Name/description match the instructions: the SKILL.md is a CLI-focused guide for modeling APIs with the 'swamp' binary and converting models into *Claw skills. Requiring the 'swamp' binary is expected. However, the included .claude/settings.local.json only whitelists a small subset of swamp commands (swamp --version, swamp auth:*, swamp extension:*), while the instructions expect broad use of many other swamp commands (model create/edit/validate/method run, workflow run, data commands). That mismatch is an incoherence to be aware of.
Instruction Scope
The SKILL.md contains many commands that create, edit, test, and publish models and extensions—and explicitly describes exporting Swamp models to generate new SKILL.md files and pushing extensions to a registry. Generating and publishing new agent skills/extensions is powerful (it can expand an agent's capabilities and add new code/files). This is coherent with the stated purpose but increases the security surface; it requires careful auditing of any generated SKILL.md or extension before enabling or publishing. Additionally, the whitelist in .claude/settings.local.json does not include many of the model/workflow commands the instructions expect to run, creating an operational inconsistency.
Install Mechanism
This is an instruction-only skill with no install spec or code files. That is low-risk from an installation standpoint — nothing will be downloaded or written by the skill itself during install.
Credentials
The skill declares no required environment variables or credentials. The SKILL.md mentions optional env vars (SWAMP_CLUB_URL) and referencing secrets via Swamp's vault (vault.get), which is consistent with the tool's expected behavior and does not demand unrelated credentials from the user.
Persistence & Privilege
The skill is not always-enabled and uses the platform-default ability to be invoked autonomously. The real privilege risk comes from the documented ability to generate and publish new *Claw skills/extensions: if an agent is permitted to create and auto-install such artifacts, its capabilities can be extended. The skill itself does not declare persistent system-wide changes, but follow-up actions (publishing/pulling extensions, writing SKILL.md files) could alter agent behavior if allowed.
What to consider before installing
This skill largely does what it says (it documents how to use the 'swamp' CLI to model APIs and export models into new *Claw skills), but there are a few things to check before installing or running it:
- Verify the 'swamp' binary: ensure it comes from a trusted source (e.g., the official GitHub repo mentioned) and is the version you expect. The skill requires that binary to exist on PATH.
- Review .claude/settings.local.json: the file that ships with the skill only whitelists a few swamp subcommands but the SKILL.md expects broad use of many commands. Confirm what commands your agent will actually be allowed to run and reconcile any permission gaps.
- Be cautious with authentication flows: 'swamp auth login' may open a browser or accept username/password flags. Avoid entering credentials into unfamiliar registries; prefer browser/OAuth flows and verify the SWAMP_CLUB_URL before logging in.
- Audit generated artifacts: the workflow explicitly instructs exporting models and generating SKILL.md (new skills) and pushing/pulling extensions. Always review any generated SKILL.md, extension manifest, or packaged extension before installing or publishing — these artifacts can add new capabilities to your agent.
- Use least privilege and sandboxing: run initial experiments in a sandboxed environment or VM, and avoid granting broad system access or persistent install rights until you have validated the tool and its outputs.
If you want a stronger conclusion, provide the actual 'swamp' binary source (checksums or install instructions) and the agent's runtime permission policy so I can re-evaluate the whitelist/permission mismatch and the potential blast radius of auto-published extensions.Like a lobster shell, security has layers — review code before you run it.
latestvk970yjj9rwppjnmx4z1etqd6xd8203pz
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
Runtime requirements
🐊 Clawdis
Binsswamp