BD skill-drift-guard
DriftGuard Security Scanner+ is a local-first security drift scanner for repos, OpenClaw skills, and AI agent tools. Use to scan before trust, save trusted baselines, compare after updates, generate human review tickets, review file/hash drift, dependency drift, install-hook changes, symlink changes, prompt-injection signals, sensitive-path references, obfuscation, shell execution, network access, and risky capability diffs.
As a process D 48/100 · Unfinished process — weak spots: result and completion, inputs and preconditions, consistency
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
- 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 · 2
✓ No critical or high findings
Medium and low: 2
-
medium Instruction override
en-ignore-previousscripts/rules.js:213Instruction-override phrase ("ignore previous instructions") (detector / deny-list definition)rationale: "Attempts to override prior instructions can hijack agent behavior when loaded into an LLM context.",
detector
A further 1 matches are quotations in this security skill's documentation and are not counted as findings.
Files scanned: 7. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 48/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 4 mutating operations with no state check
- 40Consistency. Frontmatter name (skill-drift-guard) differs from the folder (driftguard)
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash, web, git) that frontmatter does not declare
- 60Failures and branches. 2 branches
- 100Steps. 30 steps
- 100Execution cost. Instruction body is 1230 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
- -34 of 5 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +3Description length 428: enough signal without eating the budget
- +4Structure: 12 headings
- +3Step-by-step instructions: 30 items
- +4Has examples (10 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.