Pith Number

pith:BPNRV46A

pith:2026:BPNRV46AGPCWTLEUKWGGABYUGM

not attested not anchored not stored refs resolved

Do Skill Descriptions Tell the Truth? Detecting Undisclosed Security Behaviors in Code-Backed LLM Skills

Bang Fu, Baoning Niu, Huan Xing, Wenhui He, Xing Fan, Yue Li, Zehua Zhang

LLM skill descriptions often omit security-relevant operations performed by their code implementations, which SKILLSCOPE detects via source-level graphs.

arxiv:2605.12875 v1 · 2026-05-13 · cs.CR

Open paper page JSON Open Graph Bundle Merged state Verified badge What is a Pith Number?

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{BPNRV46AGPCWTLEUKWGGABYUGM}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge

Record completeness

1 Bitcoin timestamp

2 Internet Archive

3 Author claim open · sign in to claim

4 Citations open

5 Replications open

✓ Portable graph bundle live · download bundle · merged state

The bundle contains the canonical record plus signed events. A mirror can host it anywhere and recompute the same current state with the deterministic merge algorithm.

Claims

C1strongest claim

On 4,556 programmatic skills with double-blind human review, SKILLSCOPE achieves a precision of 84.8% and a recall of 96.5% for identifying inconsistency. Confirmed inconsistency affects 9.4% of skills.

C2weakest assumption

The 11-category taxonomy constructed from 920 manually analyzed skills is assumed to comprehensively cover all security-relevant operations that could appear in implementations, with no major categories missed or over-generalized.

C3one line summary

SKILLSCOPE detects undisclosed security behaviors in LLM skill implementations via security property graphs and taxonomy-based consistency checking, identifying confirmed inconsistencies in 9.4% of 4,556 evaluated skills with 84.8% precision and 96.5% recall against human review.

References

31 extracted · 31 resolved · 3 Pith anchors

[1] Extend claude with skills, 2026

[2] GitHub, “About agent skills,” https://docs.github.com/en/copilot/concepts/ agents/about-agent-skills, 2026, gitHub Docs. Accessed: 2026-04-14 2026

[3] OpenAI, “Skills in chatgpt,” 2026, official documentation. [Online]. Available: https://help.openai.com/en/articles/20001066-skills-in-chatgpt 2026

[4] Creating agent skills for github copilot, 2026

[5] Anthropic, “Claude code overview,” https://docs.anthropic.com/en/ docs/agents-and-tools/claude-code/overview, 2026, claude Code Docs. Accessed: 2026-04-14 2026

Receipt and verification

First computed	2026-05-18T03:09:11.227530Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

0bdb1af3c033c569ac94558c600714332b84b62a906f1200529920e5b5cc09a7

Aliases

arxiv: 2605.12875 · arxiv_version: 2605.12875v1 · doi: 10.48550/arxiv.2605.12875 · pith_short_12: BPNRV46AGPCW · pith_short_16: BPNRV46AGPCWTLEU · pith_short_8: BPNRV46A

Agent API

Resolver JSON Graph JSON Events JSON Schema Signing key

Verify this Pith Number yourself

curl -sH 'Accept: application/ld+json' https://pith.science/pith/BPNRV46AGPCWTLEUKWGGABYUGM \
  | jq -c '.canonical_record' \
  | python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: 0bdb1af3c033c569ac94558c600714332b84b62a906f1200529920e5b5cc09a7

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "de19fec0b81d82ee05fe2e40f067b9d10a6dea595a899383d8f98fa002f81c75",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CR",
    "submitted_at": "2026-05-13T01:44:10Z",
    "title_canon_sha256": "18bf03000c89e0ae0d96318e5b3d246331023ca28717cf77554c1fd848db642c"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.12875",
    "kind": "arxiv",
    "version": 1
  }
}