BD openguardrails
Runtime security plugin for AI agents. Provides local-first protection against data exfiltration, credential theft, command injection, and sensitive data leakage. Includes a free AI Security Gateway that sanitizes PII before it reaches LLM providers. Fully open source (Apache 2.0) — all detection and sanitization logic is auditable on GitHub. Source: github.com/openguardrails/openguardrails
Runtime security plugin for AI agents.
As a process D 35/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
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 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.
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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 · 1
✓ No critical or high findings
Medium and low: 1
-
medium Instruction override
en-ignore-previousSKILL.md:312Instruction-override phrase ("ignore previous instructions") (documentation of a security skill)| Instruction override | Attempts to override or discard prior context | `__REDACTED_BY_OPENGUARDRAILS_DUE_TO_PROMPT_INJECTION__` |
security skill
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - warning
body-longSKILL.md body ≈ 5509 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 35/100
- 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. 13 mutating operations with no state check
- 40Consistency. Frontmatter name (openguardrails) differs from the folder (og-openclawguard-test)
- 60Tools and files. Uses tools (bash, read, web) that frontmatter does not declare
- 70Execution cost. Instruction body is 5509 tokens
- 85Steps. 51 steps, 2 vague phrases
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 14 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (9 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)
- +3Output format is not stated: the model decides each time
- -2localhost URLs: will not work for another user
- +1No license
- +2Single-language instructions
- +3Description length 393: enough signal without eating the budget
- +4Structure: 36 headings
- +3Step-by-step instructions: 51 items
- +4Has examples (18 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 60.