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 semi-trusted-rolesgit 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/semi-trusted-roles)<a href="https://agentmods.dev/skills/plamentsv/plamen/semi-trusted-roles"><img src="https://agentmods.dev/badge/skills/plamentsv/plamen/semi-trusted-roles/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/plamentsv/plamen/semi-trusted-roles"><img src="https://agentmods.dev/badge/skills/plamentsv/plamen/semi-trusted-roles.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Anti-Refusal · line 200 Skill instructs the agent to never refuse or to always comply. Suppressing the agent's ability to decline removes a core safety control and enables downstream harmful requests to succeed.Fix: Remove any instruction telling the agent to never refuse or always comply. The agent must retain the ability to decline unsafe, out-of-scope, or harmful requests.
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 | $0.00029 | $0.03166 |
| Opus 5 | $0.00015 | $0.01583 |
| Sonnet 5 | $0.00006 | $0.00633 |
| Haiku 4.5 | $0.00003 | $0.00317 |
Grade A, and why
semi-trusted-roles 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 10d 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 — 285 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SEMI_TRUSTED_ROLES Skill
Trigger Pattern: SEMI_TRUSTED_ROLE flag (required) Inject Into: Breadth agents, depth-state-trace Purpose: Analyze semi-trusted roles in Aptos Move protocols using capability-based access control, modeling both role-to-user and user-to-role attack vectors
Trigger Patterns
signer|SignerCapability|AdminCap|OperatorCap|KeeperCap|has_role|
assert_admin|assert_operator|friend|acquires|ExtendRef|
DeleteRef|TransferRef|MintRef|BurnRef
Reasoning Template
Step 1: Inventory Role Permissions
Enumerate ALL privileged roles in the protocol:
| Role | Capability / Check | Module | Functions Callable | State Modifiable | External Calls |
|---|---|---|---|---|---|
| {role} | {SignerCapability / custom Cap struct / signer check / friend} | {module} | {fn list} | {state list} | {calls list} |
Aptos capability patterns to inventory:
- SignerCapability: Stored in resource, allows generating a signer for the capability's address. Can call any function requiring that signer.
- Custom capability structs:
AdminCap,OperatorCapetc. -- often stored in the deployer's account or an Object - Signer checks:
assert!(signer::address_of(account) == @admin, E_NOT_ADMIN)-- direct address comparison - Friend declarations:
friend module::other-- allowsotherto callpublic(friend)functions - Object Refs:
ExtendRef,DeleteRef,TransferRef,MintRef,BurnRef-- object-level capabilities - Resource account patterns: Module creates a resource account and stores its
SignerCapability
For each role at {ROLE_FUNCTIONS}:
- What state does it modify?
- What external calls does it make (via CPI or module calls)?
- What parameters does it accept?
Step 2: Analyze Within-Scope Abuse (Direction A: Malicious Role)
For each permitted action, ask:
Timing Abuse:
- Can {ROLE_NAME} execute at harmful times? (front-run users via transaction ordering, during rebalance)
- Can {ROLE_NAME} delay execution to harm users? (withhold keeper actions)
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.
- 10d ago First seen · 285 lines · 29 tokens per session scan A 47edb34f927e
semi-trusted-roles is a skill published in the GitHub repository PlamenTSV/plamen (295 stars, last pushed 2d ago), licensed MIT. It adds 29 tokens to every session and 3,166 once invoked, about $0.0001 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.
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.
web3-grep-arsenal
Master grep command arsenal for Web3 smart contract auditing. Use when starting a new protocol scan, before deep code review, or when hunting specific vulnerability classes.