BB proton-pass
Manage Proton Pass vaults, items (logins, SSH keys, aliases, notes), passwords, SSH agent integration, and secret injection into applications. Use when working with Proton Pass for password management, SSH key storage, secret injection (run commands with secrets, inject into templates), environment variable injection, or generating secure passwords. Supports vault/item CRUD, sharing, member management, SSH agent operations, TOTP generation, secret references (pass://vault/item/field), template injection, and command execution with secrets.
As a process B 68/100 · Nearly there — weak spots: when it triggers, running it twice, progress reporting
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 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".
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.
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 · 6
✓ No critical or high findings
Medium and low: 6
-
medium Exfiltration
exfil-read-secret-filesSKILL.md:333Reads credential / secret files (documentation of a security skill)cp ~/.ssh/id_ed25519 /tmp/id_e…emp
security skill -
low Dangerous commands
cmd-pipe-to-shellSKILL.md:16Downloads and executes remote code from an unrecognised host (pipe to shell) (documentation of a security skill; the skill's own vendor host)curl -fsSL https://proton.me/download/pass-cli/install.sh | bash
security skillvendor-host -
low Secrets in code
secret-password-literalSKILL.md:365Hard-coded password / key literal (may be an example) (quoted — discussed, not commanded)--field "password=newp…123"
quoted -
low Secrets in code
secret-password-literalSKILL.md:371Hard-coded password / key literal (may be an example) (quoted — discussed, not commanded)--field "password=newp…123"
quoted -
low Secrets in code
secret-password-literalSKILL.md:391Hard-coded password / key literal (may be an example) (quoted — discussed, not commanded)--field "api_key=sk_l…123" \
quoted -
low Secrets in code
secret-password-literalSKILL.md:668Hard-coded password / key literal (may be an example)# If app logs: API_KEY: sk_l…123
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 7786 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 68/100
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 22 mutating operations with no state check
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 7786 tokens
- 100Steps. 132 steps
- 100Failures and branches. 2 branches, has a failure section
- 100Consistency. Name and required fields are in place
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 22 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)
- +1No license
- +2Single-language instructions
- +3Description length 545: enough signal without eating the budget
- +4Structure: 117 headings
- +3Step-by-step instructions: 132 items
- +3Output format is stated explicitly
- +4Has examples (88 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 77.