SKILLEMALL.ai
RU Sign in

BB adversarial-spec

Adversarial specification writer. Takes a brief (from grill-me or user) and produces a structured spec.md with YAML frontmatter, requirements, acceptance criteria, and target files. Git-aware pipeline: each run on its own branch, squash-merge on approval.

ClawHub Hermes author: chpomob v0.1.0 MIT-0 26 files · 1 script body ≈ 3 415 tokens Open the sourceclawhub.ai↗ analyzed 35 h ago

Adversarial specification writer.

As a process B 67/100 · Nearly there — weak spots: when it triggers, inputs and preconditions, progress reporting

GeneratorSoftware developmentInfrastructureAI and agentstype and topics are labelled automatically from the skill text
Runs in: OpenClaw Hermes Agent
JSON
Technical rating
B
80/100
safety, quality, tests
Safety 60%
94
Quality 40%
59
Run on models
none yet
Process rating
B
67/100
Nearly there
Inputs and preconditions w 11
0
Progress reporting w 2
0
When it triggers w 12
20
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

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.

How to improve

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
  2. For Hermes the description must be one sentence under 60 characters; move the conditions to a "When to Use" section.
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 · 2

✓ No critical or high findings

Medium and low: 2
  • medium Dangerous commands cmd-pipe-to-shell-known-host SKILL.md:24
    Pipe-to-shell installer from a well-known host (still executes remote code)
    curl -fsSL https://raw.githubusercontent.com/chpomob/adversarial-spec/main/scripts/install.sh | bash
  • low Dangerous commands cmd-pipe-to-shell-known-host scripts/install.sh:4
    Pipe-to-shell installer from a well-known host (still executes remote code) (code comment)
    #   Bootstrap (from anywhere):  curl -fsSL https://raw.githubusercontent.com/chpomob/adversarial-spec/main/scripts/install.sh | bash
    comment

Files scanned: 19. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-long-hermes description is 255 chars; the Hermes authoring standard requires ≤ 60 (one sentence, ending with a period)
  • warning description-no-when neither description nor a "## When to Use" section says when to use the skill

Process rating: all ten parameters 67/100

  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Progress reporting. Says nothing while it works
  • 20When it triggers. No condition that starts the skill
  • 60Tools and files. Uses tools (bash, web, git) that frontmatter does not declare
  • 60Consistency. The Hermes dialect needs category and tags
  • 100Steps. 37 steps
  • 100Result and completion. Output format and completion criterion are stated
  • 100Failures and branches. 1 branches, has a failure section
  • 100Execution cost. Instruction body is 3415 tokens
  • 100Running it twice. Mutating operations check current state
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 12 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)
  • -4Absolute local paths (C:\Users, /home/…): not portable
  • -45 reference files, but SKILL.md never points to them: the model will not open them
  • -31 of 3 scripts are never mentioned in SKILL.md
  • +2Single-language instructions
  • +3Description length 255: enough signal without eating the budget
  • +4Structure: 13 headings
  • +3Step-by-step instructions: 37 items
  • +3Output format is stated explicitly
  • +4Has examples (4 code blocks)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 59.

External checks

ClawHub: suspicious
This skill is a coherent spec-writing pipeline, but it gives model/provider commands broad repository mutation authority and ships unsafe install/provider examples that need review before use.
LLM: suspicious (high) · 3 Aug 2026