battle-testing-a-skill
Use when adversarially stress-testing whether a SKILL.md holds up under hostile or low-quality input -- probing a skill file for prompt-injection susceptibility, rubber-stamp or false-pass bias, over-broad mis-routing triggers, and missing rejection or escalation paths, especially to carry that adversarial-evaluation knowledge into a harness that lacks it built in. Distinct from untrusted-input-triage, which triages inbound external text before acting; this evaluates a skill file's own robustness.
Pinned to revision 1d6444696221, so it is the text this page describes rather than whatever the author pushed since.
Files
- skills/battle-testing-a-skill/SKILL.md
- skills/battle-testing-a-skill/metadata/gitapex.yaml
- skills/battle-testing-a-skill/references/adversarial-dimensions.md
- skills/battle-testing-a-skill/references/codex-model-routing.md
- skills/battle-testing-a-skill/references/provenance-and-caveats.md
- skills/battle-testing-a-skill/scripts/gitapex_route_test_model.py
- skills/battle-testing-a-skill/scripts/test_gitapex_route_test_model.py
Every link opens the file at its source, pinned to the revision this page describes.