Bitfence - pre-transaction risk infrastructure for AI agents operating on-chain
v0.5.1Provides pre-transaction risk assessments for token trades on Solana and Base, returning safety recommendations via rapid, paid oracle queries.
⭐ 1· 66·0 current·0 all-time
by@bilsbys
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
Capability signals
These labels describe what authority the skill may exercise. They are separate from suspicious or malicious moderation verdicts.
OpenClaw
Benign
medium confidencePurpose & Capability
Name/description align with the instructions: the SKILL.md only instructs the agent to call a public Bitfence API for token risk scoring on Solana and Base. The fact that checks are paid via on-chain x402 payments is documented in the instructions and is a plausible capability for a risk-oracle; no unrelated credentials, binaries, or installs are requested.
Instruction Scope
Instructions are narrowly scoped to HTTP calls to api.bitfence.ai and to presenting results to the user. The skill explicitly forbids sending wallet addresses and warns about asking consent before contextual requests and paid checks. Note: it relies on the agent/platform wallet integration to perform x402 payments, so the agent must prompt/obtain explicit user consent before any on-chain payment—this is documented but depends on correct agent behavior.
Install Mechanism
No install spec and no code files — instruction-only skill. This is lowest-risk for disk persistence or arbitrary code installation.
Credentials
The skill requires no environment variables, keys, or config paths. The only sensitive action is a paid on-chain x402 charge (drawn from the user's wallet), which is appropriate to be handled by the user's wallet integration rather than environment secrets. The SKILL.md documents consent and cost transparency requirements.
Persistence & Privilege
always is false and there are no installation actions that modify other skills or system settings. The skill is user-invocable and can be called autonomously by the agent (platform default); the SKILL.md places explicit constraints around paid calls and consent.
Assessment
This skill appears internally consistent: it only tells the agent to query a public API for token risk scores and to present results to the user. Before using it, confirm the agent will: (1) always prompt you and obtain explicit consent before initiating any paid x402 call from your wallet, (2) never call the contextual endpoint or send position-size data without your opt-in, and (3) rate-limit checks (avoid repeated polling). Also note the skill's source/homepage are not provided; if you need stronger assurances, ask the publisher for provenance (official site, audit, or repo) and prefer manual invocation or whitelisting so the agent cannot charge your wallet without explicit, per-call approval.Like a lobster shell, security has layers — review code before you run it.
latestvk9794p6mx6gv4mzdk0q6ft30yx84pae0
License
MIT-0
Free to use, modify, and redistribute. No attribution required.