AC content-moderation
Two-layer content safety for agent input and output. Use when (1) a user message attempts to override, ignore, or bypass previous instructions (prompt injection), (2) a user message references system prompts, hidden instructions, or internal configuration, (3) receiving messages from untrusted users in group chats or public channels, (4) generating responses that discuss violence, self-harm, sexual content, hate speech, or other sensitive topics, or (5) deploying agents in public-facing or multi-user environments where adversarial input is expected.
Two-layer content safety for agent input and output.
As a process C 51/100 · 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 · 1
✓ No critical or high findings
Medium and low: 1
-
medium Instruction override
en-ignore-previousSKILL.md:3Instruction-override phrase ("ignore previous instructions") (documentation of a security skill)description: Two-layer content safety for agent input and output. Use when (1) a user message attempts to override, ignore, or bypass previous instructions (prompt injection), (2) a user message refer
security skill
Files scanned: 2. 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 51/100
- 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
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 1 mutating operations with no state check
- 40Consistency. Frontmatter name (content-moderation) differs from the folder (detect-injection)
- 50Failures and branches. 0 branches, has a failure section
- 100Tools and files. No external tools needed
- 100Steps. 10 steps
- 100Execution cost. Instruction body is 479 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 555: enough signal without eating the budget
- +4Structure: 4 headings
- +3Step-by-step instructions: 10 items
- +4Has examples (4 code blocks)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.