DC surrealdb-memory
A comprehensive knowledge graph memory system with semantic search, episodic memory, working memory, automatic context injection, and per-agent isolation.
Not recommendedlow grade D
As a process C 58/100 · Has gaps — weak spots: result and completion, when it triggers, consistency
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Dangerous commands medium severity
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
If you install
The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.
For the author
Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
For the model run — optional
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 19
✓ No critical or high findings
Medium and low: 19
-
medium Dangerous commands
cmd-pipe-to-shellCHANGELOG.md:49Downloads and executes remote code from an unrecognised host (pipe to shell) (documentation of a security skill)- **`scripts/install.sh`** — Added `⚠️ SECURITY NOTICE` banner explaining the curl|sh risk; added `--skip-surreal` flag to bypass network installer entirely; added explicit `y/N` confirmation gate wit
security skill -
medium Dangerous commands
cmd-pipe-to-shellINSTRUCTIONS.md:9Downloads and executes remote code from an unrecognised host (pipe to shell) (documentation of a security skill)**Option A: Automatic (runs curl | sh)**
security skill -
medium Dangerous commands
cmd-pipe-to-shellscripts/install.sh:10Downloads and executes remote code from an unrecognised host (pipe to shell) (code comment)# To use the curl|sh network installer, pass --install-surreal:
comment -
medium Dangerous commands
cmd-pipe-to-shellscripts/install.sh:13Downloads and executes remote code from an unrecognised host (pipe to shell) (code comment)# Running scripts directly from the internet via curl|sh is
comment -
medium Dangerous commands
cmd-pipe-to-shellscripts/install.sh:87Downloads and executes remote code from an unrecognised host (pipe to shell) (the skill's own vendor host)curl -sSf https://install.surrealdb.com | sh
vendor-host -
medium Dangerous commands
cmd-pipe-to-shellscripts/install.sh:93Downloads and executes remote code from an unrecognised host (pipe to shell) (the skill's own vendor host)curl -sSf https://install.surrealdb.com | sh
vendor-host -
medium Dangerous commands
cmd-pipe-to-shellSECURITY.md:101Downloads and executes remote code from an unrecognised host (pipe to shell) (documentation of a security skill)- [ ] Install SurrealDB manually (not via curl|sh)
security skill -
medium Dangerous commands
cmd-pipe-to-shellskill.json:150Downloads and executes remote code from an unrecognised host (pipe to shell) (string literal in code, not executed)"1. Install SurrealDB manually from https://surrealdb.com/install (do NOT use scripts/install.sh's curl|sh path)",
code literal -
low Dangerous commands
cmd-pipe-to-shellINSTRUCTIONS.md:17Downloads and executes remote code from an unrecognised host (pipe to shell) (documentation of a security skill; the skill's own vendor host)curl -sSf https://install.surrealdb.com | sh
security skillvendor-host -
low Dangerous commands
cmd-pipe-to-shellopenclaw-integration/gateway/memory.ts:219Downloads and executes remote code from an unrecognised host (pipe to shell) (string literal in code, not executed; the skill's own vendor host)const { stdout, stderr } = await execAsync("curl -sSf https://install.surrealdb.com | sh", {code literalvendor-host -
low Dangerous commands
cmd-pipe-to-shellpackage.json:79Downloads and executes remote code from an unrecognised host (pipe to shell) (string literal in code, not executed; the skill's own vendor host)"description": "Runs 'curl -sSf https://install.surrealdb.com | sh' to install SurrealDB binary",
code literalvendor-host -
low Dangerous commands
cmd-pipe-to-shellpackage.json:122Downloads and executes remote code from an unrecognised host (pipe to shell) (string literal in code, not executed; the skill's own vendor host)"This skill executes 'curl https://install.surrealdb.com | sh' - review the installer URL before running",
code literalvendor-host -
low Dangerous commands
cmd-pipe-to-shellscripts/web-ui.py:273Downloads and executes remote code from an unrecognised host (pipe to shell) (string literal in code, not executed; the skill's own vendor host)["sh", "-c", "curl -sSf https://install.surrealdb.com | sh"],
code literalvendor-host -
low Dangerous commands
cmd-pipe-to-shellscripts/web-ui.py:280Downloads and executes remote code from an unrecognised host (pipe to shell) (string literal in code, not executed; the skill's own vendor host)["sh", "-c", "curl -sSf https://install.surrealdb.com | sh"],
code literalvendor-host -
low Dangerous commands
cmd-pipe-to-shellskill.json:79Downloads and executes remote code from an unrecognised host (pipe to shell) (detector / deny-list definition; string literal in code, not executed; the skill's own vendor host)"description": "scripts/install.sh can run 'curl -sSf https://install.surrealdb.com | sh' to install SurrealDB. This is NOT recommended. Install SurrealDB manually from https://surrealdb.com/install."
detectorcode literalvendor-host
A further 4 matches are quotations in this security skill's documentation and are not counted as findings.
Files scanned: 34. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - warning
body-longSKILL.md body ≈ 5421 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 58/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 5 mutating operations with no state check
- 40Consistency. Frontmatter name (surrealdb-memory) differs from the folder (surrealdb-knowledge-graph-memory)
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 70Execution cost. Instruction body is 5421 tokens
- 100Steps. 92 steps
- 100Inputs and preconditions. Inputs and preconditions are listed
- 100Failures and branches. 1 branches, has a failure section
- low 17 top-level sections: this looks like several domains in one skill
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- -2localhost URLs: will not work for another user
- -34 of 15 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +3Description length 154: enough signal without eating the budget
- +4Structure: 44 headings
- +3Step-by-step instructions: 92 items
- +4Has examples (19 code blocks)
- +4Reference files are cited in the instructions (1 of 3)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 61.
External checks
ClawHub: suspicious
This memory skill is mostly transparent about what it does, but it exposes powerful install, repair, service-start, source-patching, secret-handling, and background-memory behaviors that need careful review before use.
LLM: suspicious (high) · VirusTotal: suspicious · 28 May 2026