BF injection-spotter
Spot prompt-injection in untrusted content before an agent acts on it — the anatomy of injected instructions across the channels attackers use (email, web, files, tool outputs, documents), the tell-list, and the safe-handling response. Use when asked is this content trying to hijack my agent, check this page or email or file for prompt injection, spot the injection, or why did my agent go off-task. Produces the injection verdict with quoted tells, the channel-specific patterns, and the safe-handling protocol.
Spot prompt-injection in untrusted content before an agent acts on it — the anatomy of injected instructions across the channels attackers use (email, web…
As a process F 51/100 · Will not run — References files that are not bundled: ../email-agent-preflight/SKILL.md, ../browser-agent-preflight/SKILL.md, ../file-access-preflight/SKILL.md
How to improve
- The text references files that are not there: add them or drop the references.
- 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
✓ Guard found no suspicious behaviour. 5 matches are attack strings quoted in this security skill's own documentation.
Files scanned: 1. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: ../email-agent-preflight/SKILL.md - warning
missing-refreference to a missing file: ../browser-agent-preflight/SKILL.md - warning
missing-refreference to a missing file: ../file-access-preflight/SKILL.md
Process rating: all ten parameters 51/100
- 0Tools and files. 3 referenced file(s) missing: ../email-agent-preflight/SKILL.md, ../browser-agent-preflight/SKILL.md, ../file-access-preflight/SKILL.md
- 0Failures and branches. Linear process with no failure handling
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 3 mutating operations with no state check
- 60Result and completion. Output format stated, no completion criterion
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 23 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1453 tokens
- 100Progress reporting. Reports progress
- low 10 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)
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +3Description length 514: enough signal without eating the budget
- +4Structure: 12 headings
- +3Step-by-step instructions: 23 items
- +3Output format is stated explicitly
Quality base 70; lint remarks subtract, signals add up to 100. Result: 71.