ReddRadar
Topic: ai-agent
2,303 skills in this topic.
-
centralization-risk
Trigger Pattern Protocol has privileged authorities (admin, operator, upgrade authority, governance) - Inject Into Breadth agents (optional), depth-state-trace
PlamenTSV/plamen 215
-
ref-lifecycle
Type Thought-template (instantiate before use) - Trigger Pattern Always (Aptos Move) -- ConstructorRef/TransferRef/MintRef/BurnRef lifecycle
PlamenTSV/plamen 215
-
reentrancy-analysis
Trigger REENTRANCY flag detected (dynamic dispatch, closures, dispatchable FA, function values) - Used by Breadth agents, depth-state-trace
PlamenTSV/plamen 215
-
semi-trusted-roles
Type Thought-template (instantiate before use) - Research basis Insider threat modeling, keeper/bot abuse vectors
PlamenTSV/plamen 215
-
dex-integration-security
Protocol Type Trigger dex_integration (detected when recon finds swap|addLiquidity|removeLiquidity|IUniswapV2Router|ISwapRouter|amountOutMin|amountOutMinimum|slippage - AND the...
PlamenTSV/plamen 215
-
account-abstraction-security
Protocol Type Trigger account_abstraction (detected when ERC-4337 interfaces, EntryPoint, UserOperation, or Paymaster patterns found) - Inject Into Breadth agents, depth-external
PlamenTSV/plamen 215
-
semantic-gap-investigator
Trigger Semantic Invariant Agent (Phase 4a.5) reports sync_gaps = 1 OR accumulation_exposures = 1 OR conditional_writes = 1 OR cluster_gaps = 1 in its return message - Agent Typ...
PlamenTSV/plamen 215
-
semantic-consistency-audit
Trigger HAS_MULTI_CONTRACT flag in template_recommendations.md (recon detects 2+ in-scope contracts/modules sharing parameters or formulas) - Agent Type general-purpose (standal...
PlamenTSV/plamen 215
-
multi-step-operation-safety
Niche agent for multi-step operation safety: authorization sequence conflicts in batch/multi-step operations, and infrastructure address targeting via public on-behalf-of functions
PlamenTSV/plamen 215
-
event-completeness
Trigger MISSING_EVENT flag in template_recommendations.md (recon detects admin/state-changing functions without events) - Agent Type general-purpose (standalone niche agent, NOT...
PlamenTSV/plamen 215
-
dimensional-analysis
Trigger MIXED_DECIMALS flag (mulDiv/mulWad/rayMul + mixed scale factors detected) - standalone niche agent, 1 budget slot
PlamenTSV/plamen 215
-
external-precondition-audit
Trigger Pattern Any external module interaction detected in attack_surface.md - Inject Into Breadth agents (merged via M5 hierarchy)
PlamenTSV/plamen 215
-
external-precondition-audit
Trigger Pattern Any external contract interaction detected in attack_surface.md - Inject Into Breadth agents (merged via M7 hierarchy)
PlamenTSV/plamen 215
-
migration-analysis
Trigger Protocol has migration patterns (reinitializer, V2/V3, deprecated, upgrade, legacy) - Covers Token type mismatches, stranded assets, interface incompatibilities
PlamenTSV/plamen 215
-
oracle-analysis
Trigger Pattern ORACLE flag (required) - Inject Into Breadth agents, depth-external, depth-edge-case
PlamenTSV/plamen 215
-
economic-design-audit
Trigger Pattern MONETARY_PARAMETER flag (required) - Inject Into Breadth agents (merged via M6 hierarchy)
PlamenTSV/plamen 215
-
token-flow-tracing
Performs comprehensive token flow analysis by tracing all token entry and exit paths, verifying accounting consistency, detecting unsolicited transfer vectors, and identifying risks such as donation attacks, balance desynchronization, token type confusion, and side-effect-driven state changes.
PlamenTSV/plamen 215
-
callback-receiver-safety
Niche agent for callback receiver safety: access control on implemented callback handlers, permissionless state inflation via callbacks, and selective revert exploitation
PlamenTSV/plamen 215
-
ability-analysis
Trigger Pattern Always (Aptos Move) - foundational security check - Inject Into Breadth agents, depth agents
PlamenTSV/plamen 215
-
vault-accounting
Protocol Type Trigger vault (detected in recon TASK 0 Step 1) - Inject Into Core state agent OR economic design agent (merge via M4 hierarchy)
PlamenTSV/plamen 215
-
centralization-risk
Trigger Protocol has privileged roles (admin, operator, governance, resource account owner) - Covers Single points of failure, privilege escalation, external governance dependen...
PlamenTSV/plamen 215
-
outcome-determinism
Protocol Type Trigger outcome_determinism - detected when EITHER of these code patterns are present - - Selection from finite depletable pool with fallback behavior (while(full)...
PlamenTSV/plamen 215
-
verification-protocol
How to prove a hypothesis is TRUE or FALSE using Foundry tests.
PlamenTSV/plamen 215
-
flash-loan-interaction
Trigger Pattern FLASH_LOAN flag (required) or BALANCE_DEPENDENT flag (optional complement) - Inject Into Breadth agents, depth-token-flow, depth-edge-case
PlamenTSV/plamen 215