BD openclaw-prompt-shield
Local input-hardening scanner for OpenClaw agents. Pattern-based detection across 9 categories of LLM input risks, with combined-signal scoring and caller-supplied whitelists. Returns risk score 0-100, matched categories, a suggested sanitized version, and a safe-to-process verdict. Pure Python standard library, no remote calls, no API keys, no LLM.
As a process D 43/100 · 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 instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".
If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- 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 · 5
✓ No critical or high findings
Medium and low: 5
-
medium Exfiltration
exfil-read-secret-filesscripts/_patterns.py:274Reads credential / secret files (detector / deny-list definition)(r"\b(?:cat|less|more|head|tail)\s+(?:/etc/passwd|/etc/shadow|/proc/self|~/\.ssh/|~/\.aws/|~/\.gnupg/|~/\.config/)", "tool_abuse"),
detector -
low Dangerous commands
cmd-pipe-to-shellscripts/_patterns.py:272Downloads and executes remote code from an unrecognised host (pipe to shell) (detector / deny-list definition; string literal in code, not executed)(_ws("execute", r"(?:curl|wget|bash|sh|powershell|cmd|python|perl|ruby)"), "tool_abuse"),detectorcode literal -
low Dangerous commands
cmd-pipe-to-shellscripts/_patterns.py:273Downloads and executes remote code from an unrecognised host (pipe to shell) (detector / deny-list definition; string literal in code, not executed)(_ws("run", r"(?:curl|wget|bash|sh|powershell|cmd)", r"[-/]"), "tool_abuse"),detectorcode literal
A further 2 matches are quotations in this security skill's documentation and are not counted as findings.
Files scanned: 12. 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")
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. 5 mutating operations with no state check
- 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
- 100Steps. 50 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2958 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 15 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)
- +3Output format is not stated: the model decides each time
- -31 of 6 scripts are never mentioned in SKILL.md
- +2Single-language instructions
- +3Description length 351: enough signal without eating the budget
- +4Structure: 21 headings
- +3Step-by-step instructions: 50 items
- +4Has examples (9 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 74.