nwave-ai/nw-canary
NewSkillScoreMaintainedCanary skill for auto-injection detection
by nwave-ai
Links this skill to your agents and keeps it current with the author’s updates.
On-demandOn-demand: invoked explicitly — never occupies your agent's context until called.
◆QA & Test Engineering pack
1 · One-time — install the CLI (
docs ↗)
$pip install decimalai
2 · Get the skill — writes .claude/skills/nwave-ai-nw-canary/SKILL.md
$decimalai skills pull nwave-ai-nw-canary --out .claude/skills/
No CLI? Get the same file — curl · raw file
$curl -fsSL --create-dirs -o .claude/skills/nwave-ai-nw-canary/SKILL.md https://app.decimal.ai/s/nwave-ai-nw-canary/SKILL.md
how this skill behaves on real traffic · last 30 days
No production data for this skill yet — usage numbers appear here once agents start running it.
Anonymized aggregate across every org using this skill — proof from real production use, not a demo.
Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents 23 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 3h ago
—-39% tokens0% turns87% of whole cases pass with skill (20/23)
Showing 5 of 23 cases
SkillSafety
✓ 3 of 3 passed✓Code scan15 of 15 checks clean
0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026
live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing
✓IntentSafe
LLM judge · does the skill do what it claims
✓ContentClean
LLM judge · policy & harmful-content review
Source
ImportedLicense MITImported 8/3/2026Version v1
Canary Skill
This skill exists solely for injection detection (ADR-006).
If you can read this content without explicitly loading the file, auto-injection is active and working.
Passphrase: NWAVE_SKILL_INJECTION_ACTIVE_2026
Do not modify this file. Its content integrity is verified by automated tests in tests/canary/test_skill_injection.py.
Want to see if nwave-ai/nw-canary would activate on your phrasing? Try it before you install — no LLM call, no signup.