SKILLEMALL.ai

FD openclaw-bastion

(no description)

Not recommendedcritical or high security findings · low grade F
ClawHub Agent Skills author: AtlasPA v1.0.2 4 files body ≈ 1 118 tokens Open the sourceclawhub.ai analyzed 3 d ago

As a process D 49/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions

ProcedureInfrastructuretype and topics are labelled automatically from the skill text
JSON
Technical rating
F
36/100
safety, quality, tests
Safety 60%
34
Quality 40%
39
Run on models
none yet
Process rating
D
49/100
Unfinished process
Result and completion w 14
0
When it triggers w 12
0
Inputs and preconditions w 11
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.

Dangerous commands
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.

Instruction override 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 text contains phrases like "ignore previous instructions" or "you are now…". That is an attempt to hijack the agent: it may break your rules, the system limits or company policy.

For the author

An honest skill does not need them: state the role and the rules directly without overriding other instructions. Otherwise catalog scanners and corporate filters will block the listing.

Concealment 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 tells the agent to hide things from you: not to show errors, not to mention actions, to report differently from what was done. You lose the ability to see what the agent really did.

For the author

Transparency beats a smooth answer. If the goal is to hide technical noise, ask the agent to "summarise briefly", not to "not mention".

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.
  2. Add a description to the frontmatter: without it the skill never triggers.
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 · 13

  • high Dangerous commands cmd-destructive-fs scripts/bastion.py:225
    Destructive filesystem command (wipes root/home/drive) (string literal in code, not executed)
    ":(){ :|:& };:",
    code literal
Medium and low: 12
  • medium Instruction override en-ignore-previous README.md:56
    Instruction-override phrase ("ignore previous instructions") (quoted — discussed, not commanded)
    - **Instruction override** — "ignore previous instructions", "disregard above", "you are now", "new system prompt", "forget your instructions", "override safety", "entering developer mode"
    quoted
  • medium Concealment en-hide-from-user README.md:58
    Instruction to hide actions from the user (detector / deny-list definition)
    - **Hidden instructions** — Multi-turn manipulation ("in your next response, you must..."), stealth patterns ("do not tell the user", "hide this from the output")
    detector
  • medium Dangerous commands cmd-pipe-to-shell README.md:66
    Downloads and executes remote code from an unrecognised host (pipe to shell) (detector / deny-list definition)
    - **Dangerous commands** — `curl | bash`, `wget | sh`, `rm -rf /`, fork bombs
    detector
  • medium Instruction override en-ignore-previous scripts/bastion.py:94
    Instruction-override phrase ("ignore previous instructions") (detector / deny-list definition)
    (r"(?i)ignore\s+(all\s+)?previous\s+instructions", "ignore previous instructions"),
    detector
  • medium Concealment en-hide-from-user scripts/bastion.py:120
    Instruction to hide actions from the user (detector / deny-list definition)
    (r"(?i)do\s+not\s+(tell|inform|alert|warn)\s+(the\s+)?user", "stealth: do not tell the user"),
    detector
  • medium Concealment en-hide-from-user scripts/bastion.py:121
    Instruction to hide actions from the user (detector / deny-list definition)
    (r"(?i)hide\s+this\s+(from|in)\s+(the\s+)?(user|output|response)", "stealth: hide this from user"),
    detector
  • medium Dangerous commands cmd-destructive-fs scripts/bastion.py:191
    Destructive filesystem command (wipes root/home/drive) (detector / deny-list definition; string literal in code, not executed)
    (r"(?i)rm\s+-rf\s+/(?:\s|$)", "rm -rf / (destructive)"),
    detectorcode literal
  • medium Dangerous commands cmd-destructive-fs-scoped scripts/bastion.py:227
    Destructive command on a partition / current directory (normal in admin docs; verify the target) (string literal in code, not executed)
    "dd if=/dev/zero of=/dev/*",
    code literal
  • medium Dangerous commands cmd-destructive-fs-scoped scripts/bastion.py:228
    Destructive command on a partition / current directory (normal in admin docs; verify the target) (string literal in code, not executed)
    "dd if=/dev/random of=/dev/*",
    code literal
  • low Dangerous commands cmd-privilege scripts/bastion.py:230
    Privilege escalation / world-writable permissions (string literal in code, not executed)
    "chmod 777 /",
    code literal
  • low Concealment en-hide-from-user SKILL.md:86
    Instruction to hide actions from the user (detector / deny-list definition; documentation table row)
    | **Hidden instructions** | Multi-turn manipulation ("in your next response, you must"), stealth patterns ("do not tell the user") | CRITICAL |
    detectortable
  • low Dangerous commands cmd-pipe-to-shell SKILL.md:89
    Downloads and executes remote code from an unrecognised host (pipe to shell) (detector / deny-list definition; documentation table row)
    | **Dangerous commands** | `curl \| bash`, `wget \| sh`, `rm -rf /`, fork bombs | CRITICAL |
    detectortable

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

Against the Agent Skills spec

  • error description-missing SKILL.md: no `description` — the skill can never trigger

Process rating: all ten parameters 49/100

  • 0Result and completion. Does not say what the result is
  • 0When it triggers. No condition that starts the skill
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 30Running it twice. 1 mutating operations with no state check
  • 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
  • 60Failures and branches. 2 branches
  • 100Steps. 9 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 1118 tokens
  • 100Progress reporting. Reports progress
  • 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)
  • +3Description length 0: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • +1No license
  • +2Single-language instructions
  • +4Structure: 14 headings
  • +3Step-by-step instructions: 9 items
  • +4Has examples (6 code blocks)
  • +3All 1 scripts are documented

Quality base 70; lint remarks subtract, signals add up to 100. Result: 39.

External checks

ClawHub: suspicious
This skill has a coherent security purpose, but it gives itself broad file-changing and persistent hook behavior with unsafe scoping and restoration logic.
LLM: suspicious (high) · VirusTotal: benign · 10 Sept 2026