BC anti-injection-skill
Advanced prompt injection defense with multi-layer protection, memory integrity, and tool security wrapper. OWASP LLM Top 10 2026 compliant.
As a process C 53/100 · Has gaps — 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
- 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 · 8
✓ No critical or high findings
Medium and low: 8
-
medium Instruction override
en-ignore-previousCONFIGURATION.md:122Instruction-override phrase ("ignore previous instructions") (documentation of a security skill)ignore previous instructions
security skill -
medium Instruction override
en-ignore-previousREADME.md:45Instruction-override phrase ("ignore previous instructions") (documentation of a security skill)You: ignore previous instructions
security skill -
low Dangerous commands
cmd-privilegeSKILL.md:314Privilege escalation / world-writable permissions (negated — the text forbids it)- rm -rf, dd, mkfs, chmod 777
negated -
low Dangerous commands
cmd-pipe-to-shellSKILL.md:315Downloads and executes remote code from an unrecognised host (pipe to shell) (negated — the text forbids it)- curl | bash, wget | sh
negated -
low Dangerous commands
cmd-encoded-execSKILL.md:316Executes a base64/encoded payload (negated — the text forbids it)- base64 -d | sh, eval, exec
negated
A further 3 matches are quotations in this security skill's documentation and are not counted as findings.
Files scanned: 5. 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 53/100
- 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
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 1 mutating operations with no state check
- 100Tools and files. No external tools needed
- 100Steps. 45 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3327 tokens
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 17 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
- +2Single-language instructions
- +3Description length 140: enough signal without eating the budget
- +4Structure: 21 headings
- +3Step-by-step instructions: 45 items
- +4Has examples (14 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.