Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add PlamenTSV/plamen --skill bls-aggregation-auditgit clone --depth 1 https://github.com/PlamenTSV/plamenWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/plamentsv/plamen/bls-aggregation-audit)<a href="https://agentmods.dev/skills/plamentsv/plamen/bls-aggregation-audit"><img src="https://agentmods.dev/badge/skills/plamentsv/plamen/bls-aggregation-audit.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00032 | $0.02300 |
| Opus 5 | $0.00016 | $0.01150 |
| Sonnet 5 | $0.00006 | $0.00460 |
| Haiku 4.5 | $0.00003 | $0.00230 |
Grade A, and why
bls-aggregation-audit scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Injectable Skill: BLS Aggregation Audit
L1 trigger:
L1_PATTERN=trueAND (bls/ORblstORmilagroORpairingORaggregate_signatureORproof_of_possessiondetected in recon subsystem map) Inject Into:depth-consensus-invariantordepth-externalLanguage: Go, Rust, occasionally C Finding prefix:[BLS-N]Status: v0.1 draft, Round 4 exemplars pending
Orchestrator Decomposition Guide
- Sections 1, 2: depth-consensus-invariant (protocol-level BLS use)
- Section 3: depth-external (library interface, FFI)
- Section 4: depth-edge-case (boundary inputs)
When This Skill Activates
Recon identifies BLS12-381 signature use, typically in: Ethereum beacon chain, Filecoin, Celo, Chia, Aptos, or any aggregated-signature consensus. BLS is subtle: textbook descriptions assume defenses (subgroup check, rogue-key defense) that implementations often forget.
1. Library Fingerprinting
Identify the BLS library:
| Library | Language | Canonical use |
|---|---|---|
blst |
C with Go/Rust bindings | Lighthouse, Prysm, Teku |
milagro-crypto |
C | Older clients |
arkworks |
Rust | Aptos, some academic |
celo-bls-zexe |
Rust | Celo |
py_ecc |
Python | Reference implementations |
| hand-rolled pairing | Various | Red flag — usually wrong |
A hand-rolled pairing implementation is a near-certain bug source. Flag it for intensive review.
2. Subgroup Check
BLS signatures live in a subgroup of an elliptic curve group. An attacker can provide a curve point that is valid on the curve but outside the subgroup, leading to signature verification forgeries.
Check:
- Is every received signature / public key checked for subgroup membership before use?
- In
blst, the function isblst_p1_in_g1/blst_p2_in_g2 - In
arkworks, there areis_in_correct_subgroup_assuming_on_curvehelpers - Protocol-level: when a signature is received from a peer, is subgroup-checked BEFORE aggregation with trusted signatures?
- Aggregation without subgroup check: combining a valid sig with a subgroup-invalid sig can corrupt the aggregate
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 7d ago First seen · 163 lines · 32 tokens per session scan A fef911df501f
bls-aggregation-audit is a skill published in the GitHub repository PlamenTSV/plamen (286 stars, last pushed today), licensed MIT. It adds 32 tokens to every session and 2,300 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
analyzing-ethereum-smart-contract-vulnerabilities
Perform static and symbolic analysis of Solidity smart contracts using Slither and Mythril to detect reentrancy, integer overflow, access control, and other vulnerability classes before deployment to Ethereum mainnet.
prowler-tour
Keeps product-tour definitions aligned with the UI features they describe. Trigger: When modifying UI components that have associated tours, editing tour definition files, or renaming data-tour-id attributes.
analyzing-ethereum-smart-contract-vulnerabilities
Perform static and symbolic analysis of Solidity smart contracts using Slither and Mythril to detect reentrancy, integer overflow, access control, and other vulnerability classes before deployment to Ethereum mainnet.
evm-bytecode-analysis
Analyze supplied deployed EVM runtime bytecode with EVMole or guide a separate application in integrating a published EVMole Rust, Go, Python, or JavaScript binding. Use for unverified-contract inspection, ABI reconstruction from runtime code, selector discovery, storage-access analysis, EVM control-flow inspection…
talos-action-development
Develop, modify, review, and maintain standalone Talos actions in contracts/tasks/actions, including chain guardrails, contract bindings, transaction safety, schedules, action catalogues, and Talos documentation. Use when adding an action, changing an action’s behavior or parameters, updating a Talos schedule, or…
web3-poc-foundry
Complete Foundry PoC writing guide + all cheatcodes + DeFiHackLabs reproduction patterns. Use this when building a proof of concept exploit, setting up a fork test, using Foundry cheatcodes, or reproducing a known DeFi hack for learning.