levi-qiao/longgraph-skill / skills/loop-graph
loop-graph
FlaggedUse only when the user explicitly invokes /loop-graph or names this skill. Compiles a custom loop-graph run. Do not use unless named. Existing runtime nodes are self-contained.
Security report
FlaggedStatic analysis of one exact version. It reduces risk and shows evidence; it does not certify that a skill is safe.
- Commit
3e26e19b91e62dba63c0ab53ad5ba8a670403abb- Content hash
f674ccb0e449adbc54579932525a671c4180ecdb9f418e5a42a4a9b5da03da74- Scanned
- 2026-11-17
- Scanner version
- skillxone-scan-1.0.0
- Policy version
- 0.1-draft
- Decision
- 2 open critical or high findings.
- Verification expires
- Not applicable
Findings (2 high, 6 medium)
A script is downloaded and run in one step, so whatever the server returns at that moment is executed without review.
curl -fsSL https://raw.githubusercontent.com/levi-qiao/longgraph-skill/main/install.sh | shSuggested fix: Download the script, check it (and its checksum or signature), then run the saved copy. Prefer a package manager.
A script is downloaded and run in one step, so whatever the server returns at that moment is executed without review.
curl -fsSL https://raw.githubusercontent.com/levi-qiao/longgraph-skill/main/install.sh | shSuggested fix: Download the script, check it (and its checksum or signature), then run the saved copy. Prefer a package manager.
An HTML comment contains instructions. Comments are hidden when the file is rendered, so a reader would not see them, but an agent reading the raw file would.
`/loop {{INTERVAL}} Execute the existing runtime node at {{PATH}}. Do not load any skill.`Suggested fix: Move instructions into visible text, or remove the comment.
An HTML comment contains instructions. Comments are hidden when the file is rendered, so a reader would not see them, but an agent reading the raw file would.
directives.md covers the action and its evidence bar is met, execute it — it doesSuggested fix: Move instructions into visible text, or remove the comment.
An HTML comment contains instructions. Comments are hidden when the file is rendered, so a reader would not see them, but an agent reading the raw file would.
executor always has a legal next item. On a discovery-driven run, seed the *method* — theSuggested fix: Move instructions into visible text, or remove the comment.
An HTML comment contains instructions. Comments are hidden when the file is rendered, so a reader would not see them, but an agent reading the raw file would.
Always generate this file: cold nodes depend on its exact pointers and verificationSuggested fix: Move instructions into visible text, or remove the comment.
An HTML comment contains instructions. Comments are hidden when the file is rendered, so a reader would not see them, but an agent reading the raw file would.
(`AGENTS.md`, `CLAUDE.md`, a docs map) is one row pointing at that file — re-listingSuggested fix: Move instructions into visible text, or remove the comment.
An HTML comment contains instructions. Comments are hidden when the file is rendered, so a reader would not see them, but an agent reading the raw file would.
anything, and a stale ID belonging to a session you are not in is simply replaced bySuggested fix: Move instructions into visible text, or remove the comment.
Checks run
- prompt-injection
- dangerous-commands
- credentials
- network
- file-access
- integrity
Checks skipped
- dependencies: No dependency manifest in the skill directory.
- gitleaks: gitleaks is not installed on this host.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 465k | Updated | Claude CodeCodex | Unverified | Install |
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 465k | Updated | Claude CodeCodex | Unverified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 318k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 318k | Updated | Claude CodeCodex | Verified | Install |