CC camscanner
CamScanner Official Skill — intelligent document conversion and processing. Use when the user mentions CamScanner, format conversion (image/PDF to Word/Excel/Markdown, Word/Excel/PPT to PDF, Office document format conversion, images to PDF), image enhancement/upscaling/restoration, OCR, image translation, formula extraction, watermark add/remove, multi-image merge, document scanning/editing, invoice/receipt recognition, or cloud document search/download/move/folder management. Does not support merging existing PDFs into one file.
CamScanner Official Skill — intelligent document conversion and processing.
As a process C 57/100 · Has gaps — weak spots: result and completion, consistency, execution cost
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
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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 · 4
✓ No critical or high findings
Medium and low: 4
-
medium Dangerous commands
cmd-pipe-to-shellscripts/setup.sh:7Downloads and executes remote code from an unrecognised host (pipe to shell) (code comment)# curl -fsSL <CDN>/setup.sh | sh
comment -
low Secrets in code
secret-high-entropy-tokenreferences/cloud-documents.md:113High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)camscanner-cli doc download 7DD6…rd1
detector -
low Dangerous commands
cmd-execpolicy-bypassscripts/setup.ps1:2Runs PowerShell with execution policy bypassed (code comment)# Usage: powershell -ExecutionPolicy Bypass -File scripts\setup.ps1
comment -
low Dangerous commands
cmd-execpolicy-bypassSKILL.md:77Runs PowerShell with execution policy bypassed (documentation table row; documentation of a security skill)| Windows | `powershell -ExecutionPolicy Bypass -File scripts/setup.ps1` |
tablesecurity skill
Files scanned: 17. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 8657 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "display_name" - note
frontmatter-keyunknown frontmatter key "display_name_en" - note
frontmatter-keyunknown frontmatter key "description_en" - note
frontmatter-keyunknown frontmatter key "homepage" - note
edit-residuethe text marks something as outdated (lines 342, 344, 346): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 57/100
- 0Result and completion. Does not say what the result is
- 40Consistency. Frontmatter name (camscanner) differs from the folder (cs-cli)
- 40Execution cost. Instruction body is 8657 tokens: crowds the task out of the window
- 60Tools and files. Uses tools (bash, node) that frontmatter does not declare
- 60Steps. 61 steps, 7 vague phrases
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Failures and branches. 8 branches, has a failure section
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 10 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (4 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)
- +3Output format is not stated: the model decides each time
- -31 of 4 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +3Description length 535: enough signal without eating the budget
- +4Structure: 31 headings
- +3Step-by-step instructions: 61 items
- +4Has examples (9 code blocks)
- +4Reference files are cited in the instructions (10 of 10)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 72.