Passed 20 of 22 test cases with the skill, and 14 of 22 without it.
Without skill64%
With skill91%
Checks it passed that the model alone missed
Classifies the issue as High.
Identifies process arguments.
Identifies internal hostnames.
and 4 more in the full report
6 fixed14 passed either way2 still failing0 broke
Pass-rate lift
+27 pp
Tokens
+101%
Agent turns
0%
Response time
-21%
Model gemini-3.6-flashMeasured 8/16/2026v120 of 22 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 6 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 6
Prompt
What is the initial phase in a structured information disclosure testing methodology before running diff harnesses or enumerating specific artifacts?
What was checked, without and with the skill
Checked
Without skill
With skill
Identifies building a channel map as the initial phase.
Missed
Passed
case-09 · gemini-3.6-flash · 8/16/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md178 linessingle file
Information Disclosure
Information leaks accelerate exploitation by revealing code, configuration, identifiers, and trust boundaries. Treat every response byte, artifact, and header as potential intelligence. Minimize, normalize, and scope disclosure across all channels.