SKILLEMALL.ai

AD secrets-inject

HIGH-PRIVILEGE companion to secrets-manager. Substitutes encrypted secrets into command strings and materializes them as executable shell scripts (written to chmod 0600 temp files) or prints them to stdout. This is a secret-exfiltration-capable capability by design — it intentionally expands a secret store into command material. Use ONLY when you must hand secrets to a shell command. The core secrets-manager store deliberately does NOT do this; this lives in its own skill so the dangerous capability is opt-in and clearly labeled. Requires the secrets-manager store (memory/secrets).

ClawHub Agent Skills author: jlacroix82 v1.0.0 MIT-0 4 files body ≈ 733 tokens Open the sourceclawhub.ai analyzed 3 d ago

HIGH-PRIVILEGE companion to secrets-manager.

As a process D 43/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions

ProcedurePersonal productivitytype and topics are labelled automatically from the skill text
JSON
Technical rating
A
93/100
safety, quality, tests
Safety 60%
100
Quality 40%
83
Run on models
none yet
Process rating
D
43/100
Unfinished process
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

How to improve

    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 · 0

    ✓ No critical or high findings

    Files scanned: 4. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    • note frontmatter-key unknown frontmatter key "permissions"

    Process rating: all ten parameters 43/100

    • 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
    • 0Progress reporting. Says nothing while it works
    • 20When it triggers. No condition that starts the skill
    • 30Running it twice. 3 mutating operations with no state check
    • 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
    • 100Steps. 11 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 733 tokens
    • 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
    • +1No license
    • +2Single-language instructions
    • +3Description length 588: enough signal without eating the budget
    • +4Structure: 8 headings
    • +3Step-by-step instructions: 11 items
    • +4Has examples (2 code blocks)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 83.

    External checks

    ClawHub: clean
    This skill intentionally exposes stored secrets for user-supplied commands, but it is clearly labeled, opt-in, local, and does not secretly transmit or run anything itself.
    LLM: benign (high) · VirusTotal: · 3 Aug 2026