CC use-cursor
Manage Cursor CLI tasks via tmux with security hardening
As a process C 51/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
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.
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.
- 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 · 8
✓ No critical or high findings
Medium and low: 8
-
medium Dangerous commands
cmd-destructive-fsextensions/use-cursor/index.js:49Destructive filesystem command (wipes root/home/drive) (string literal in code, not executed; code comment)* Input: task'; rm -rf /; echo '
code literalcomment -
medium Dangerous commands
cmd-destructive-fsextensions/use-cursor/index.js:50Destructive filesystem command (wipes root/home/drive) (string literal in code, not executed; code comment)* Step 1: Replace ' with '\'' → task'\''; rm -rf /; echo '\''
code literalcomment -
medium Dangerous commands
cmd-destructive-fsextensions/use-cursor/index.js:51Destructive filesystem command (wipes root/home/drive) (string literal in code, not executed; code comment)* Step 2: Wrap in '...' → 'task'\''; rm -rf /; echo '\''
code literalcomment -
medium Dangerous commands
cmd-destructive-fsextensions/use-cursor/index.js:52Destructive filesystem command (wipes root/home/drive) (code comment; quoted — discussed, not commanded)* Shell receives: literal string "task'; rm -rf /; echo '", no injection
commentquoted -
low Dangerous commands
cmd-pipe-to-shellREADME.md:28Downloads and executes remote code from an unrecognised host (pipe to shell) (documentation of a security skill; the skill's own vendor host)curl https://cursor.com/install -fsS | bash
security skillvendor-host -
low Dangerous commands
cmd-pipe-to-shellscripts/doctor.sh:25Downloads and executes remote code from an unrecognised host (pipe to shell) (string literal in code, not executed; the skill's own vendor host)echo "✗ NOT FOUND - run: curl https://cursor.com/install -fsS | bash"
code literalvendor-host -
low Dangerous commands
cmd-pipe-to-shellSKILL.md:116Downloads and executes remote code from an unrecognised host (pipe to shell) (documentation of a security skill; the skill's own vendor host)# curl https://cursor.com/install -fsS | bash
security skillvendor-host
A further 1 matches are quotations in this security skill's documentation and are not counted as findings.
Files scanned: 14. 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") - note
frontmatter-keyunknown frontmatter key "source" - note
frontmatter-keyunknown frontmatter key "homepage" - note
frontmatter-keyunknown frontmatter key "repository" - note
frontmatter-keyunknown frontmatter key "required" - note
frontmatter-keyunknown frontmatter key "clawhub"
Process rating: all ten parameters 51/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 10 mutating operations with no state check
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 60Failures and branches. 2 branches
- 100Steps. 60 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3035 tokens
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 13 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (3 tags): a typed call is more reliable
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)
- +3Description length 56: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -245 emoji in the instructions: noise for the model
- +2Single-language instructions
- +4Structure: 45 headings
- +3Step-by-step instructions: 60 items
- +4Has examples (19 code blocks)
- +3All 6 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 68.