SKILLEMALL.ai
GitHub ↗ RU Sign in

FC printing-press

Set up a new integration, connector, or CLI binding for any API. Wrap or generate a ship-ready Go CLI from an OpenAPI, HAR, or Postman spec via the lean research -> generate -> build -> shipcheck loop. Use when the user says build a CLI, wrap this API, set up a new integration, add a connector, integrate with a service, or names an API by domain.

Not recommendedcritical or high security findings · low grade F
mvanhorn/cli-printing-press Agent Skills author: mvanhorn MIT 45 files · 1 script body ≈ 1 245 tokens Open the sourcegithub.com↗ analyzed 32 h ago

Set up a new integration, connector, or CLI binding for any API.

As a process C 59/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches

IntegrationSoftware developmentAI and agentsWriting and documentstype and topics are labelled automatically from the skill text
Runs in: Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) OpenClaw Goose OpenCode
JSON
Technical rating
F
33/100
safety, quality, tests
Safety 60%
0
Quality 40%
82
Run on models
none yet
Process rating
C
59/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Failures and branches w 10
0
the three weakest of ten parameters · all ten

What is at stake

The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.

Exfiltration
If you install

The instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".

For the author

If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.

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.

Broad scope 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 asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.

For the author

Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.

How to improve

  1. Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
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 · 16

  • high Exfiltration intent-browser-credential-store phases/10-generate.md:498
    Accesses a browser credential / cookie store
    it captures cookies once via a controlled Chrome window and serves them to
  • high Exfiltration intent-browser-credential-store references/auth-companion.md:17
    Accesses a browser credential / cookie store
    `cli-printing-press`. It captures cookies once via a controlled Chrome window
  • high Exfiltration intent-browser-credential-store references/auth-companion.md:26
    Accesses a browser credential / cookie store
    the session cookies that hold modern session/JWT tokens. Chrome keeps session
  • high Exfiltration intent-browser-credential-store references/auth-companion.md:39
    Accesses a browser credential / cookie store
    session cookies). Attempting to read from live Chrome session..." from an
  • high Exfiltration intent-browser-credential-store references/browser-sniff-capture.md:222
    Accesses a browser credential / cookie store
    **When Chrome IS running**, use agent-browser to grab cookies, then ask the user to quit Chrome so browser-use can load the profile for capture:
  • high Exfiltration intent-browser-credential-store references/browser-sniff-capture.md:236
    Accesses a browser credential / cookie store
    # Grab cookies from running Chrome. $SESSION_STATE_FILE lives outside
  • high Exfiltration intent-browser-credential-store references/browser-sniff-capture.md:249
    Accesses a browser credential / cookie store
    For option 1 after cookies are saved and Chrome is quit:
Medium and low: 9
  • medium Exfiltration intent-browser-credential-store phases/06-browser-sniff-gate.md:122
    Accesses a browser credential / cookie store (quoted — discussed, not commanded)
    - **`mode: browser_http`** — **runtime is settled: ship the Chrome-compatible transport** (the generated Chrome profile plus uTLS; `UsesBrowserHTTPTransport` will be set in the generator's traffic-ana
    quoted
  • medium Exfiltration intent-browser-credential-store references/auth-companion.md:9
    Accesses a browser credential / cookie store (quoted — discussed, not commanded)
    > printed CLI's `auth login --chrome` exits with "Required cookies not in Chrome's
    quoted
  • medium Exfiltration intent-browser-credential-store references/auth-companion.md:38
    Accesses a browser credential / cookie store (quoted — discussed, not commanded)
    - The user is hitting "Required cookies not in Chrome's cookie DB (likely
    quoted
  • medium Exfiltration intent-browser-credential-store references/browser-sniff-capture.md:225
    Accesses a browser credential / cookie store (quoted — discussed, not commanded)
    > "Chrome is running. I'll grab your cookies, then need you to quit Chrome so I can browser-sniff with full page access."
    quoted
  • medium Exfiltration intent-browser-credential-store references/browser-sniff-capture.md:227
    Accesses a browser credential / cookie store (quoted — discussed, not commanded)
    > 1. **Grab session, then quit Chrome** (Recommended) — "I save your cookies via agent-browser, you quit Chrome, then I browser-sniff with browser-use using your profile. Full DOM access."
    quoted
  • medium Dangerous commands cmd-pipe-to-shell-known-host references/setup-checks.md:119
    Pipe-to-shell installer from a well-known host (still executes remote code)
    curl -fsSL https://raw.githubusercontent.com/mvanhorn/cli-printing-press/main/scripts/install.sh | bash -s -- --skills-only
  • medium Dangerous commands cmd-pipe-to-shell-known-host references/setup-checks.md:126
    Pipe-to-shell installer from a well-known host (still executes remote code)
    curl -fsSL https://raw.githubusercontent.com/mvanhorn/cli-printing-press/main/scripts/install.sh | bash -s -- --skills-only
  • medium Broad scope meta-broad-allowed-tools SKILL.md:1
    Broad tool permissions pre-approved: Bash
    allowed-tools: Bash Read Write Edit Glob Grep WebFetch WebSearch AskUserQuestion Agent
  • low Dangerous commands cmd-pipe-to-shell-known-host phases/01-preflight.md:291
    Pipe-to-shell installer from a well-known host (still executes remote code) (quoted — discussed, not commanded)
    echo "PRESS_SKILL_REINSTALL=curl -fsSL https://raw.githubusercontent.com/mvanhorn/cli-printing-press/main/scripts/install.sh | bash -s -- --skills-only"
    quoted

Files scanned: 45. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • note frontmatter-key unknown frontmatter key "min-binary-version"
  • note frontmatter-key unknown frontmatter key "created_by"

Process rating: all ten parameters 59/100

  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Failures and branches. Linear process with no failure handling
  • 30Running it twice. 6 mutating operations with no state check
  • 70When it triggers. States when to use, but not when not to
  • 100Tools and files. Tools declared in frontmatter
  • 100Steps. 4 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 1245 tokens
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing

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
  • +4No input/output examples
  • +1No license
  • +2Single-language instructions
  • +3Description length 348: enough signal without eating the budget
  • +4Structure: 4 headings
  • +3Step-by-step instructions: 4 items
  • +4Reference files are cited in the instructions (6 of 22)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.