Agentic Street

PassAudited by VirusTotal on May 12, 2026.

Overview

Type: OpenClaw Skill Name: agenticstreet Version: 1.0.3 The skill bundle is designed for DeFi operations, providing tools for fund management and investment. All network calls are to the stated `agenticstreet.ai` API or the optional `api.bankr.bot` for transaction submission, with clear warnings about trusting third-party services. The `ast-watcher.sh` script interacts with the local OpenClaw hook, sending only non-sensitive event counts and session keys, as explicitly documented. The `SKILL.md` and other documentation files contain numerous defensive instructions for the AI agent, such as 'NEVER send your API key to any domain other than `agenticstreet.ai`' and detailed 'Red Flag Patterns' for proposal monitoring, guiding the agent to identify and veto suspicious activities. There is no evidence of intentional data exfiltration, unauthorized remote control, persistence, or obfuscation designed to hide malicious behavior. The risks associated with DeFi and third-party services are transparently disclosed.

Findings (0)

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

What this means

A user may believe all trades can be reviewed and vetoed, when some trades can execute instantly and affect fund capital.

Why it was flagged

The top-level safety framing overstates LP veto/time-delay protections, while the detailed monitoring guide shows adapter trades can execute immediately without veto.

Skill content
SKILL.md: "Every trade is transparent, time-delayed, and vetoable"; monitoring.md: "Adapter proposals ... execute instantly. No veto window."
Recommendation

Clearly state in the main skill description that adapter trades are instant and non-vetoable, and require users to understand that limitation before depositing or managing funds.

What this means

If an agent or user invokes this script with a Bankr key, real USDC approvals and deposits can be submitted on-chain and may lock funds in a DeFi fund.

Why it was flagged

When BANKR_KEY is set, the script submits both approval and deposit transactions automatically using API-returned transaction data, with no interactive confirmation in the script.

Skill content
if [ -n "$BANKR_KEY" ]; then ... "Submitting USDC approval via Bankr..." ... "Submitting deposit via Bankr..."
Recommendation

Keep BANKR_KEY unset unless automatic submission is explicitly desired; add a human confirmation step, transaction preview, and amount limits before Bankr submission.

What this means

A failed local hook or network issue could cause proposal alerts to be acknowledged and not re-delivered, reducing the chance to veto a risky trade in time.

Why it was flagged

The hook delivery failure is swallowed with `|| true`, and the script then proceeds to acknowledge notifications, which can mark alerts as handled even if OpenClaw was not notified.

Skill content
curl ... "${HOOK_URL}/hooks/agent" ... || true ... curl ... "${API_URL}/notifications/ack" ...
Recommendation

Only acknowledge notifications after confirmed hook delivery, or keep failed deliveries pending for retry.

What this means

Leaking or overexposing these keys could let someone impersonate the agent, submit transactions through Bankr, or trigger local agent hooks.

Why it was flagged

The skill discloses credential use, but those credentials represent account identity, transaction submission authority, and local hook access.

Skill content
AST_API_KEY ... "API key for authenticated write endpoints"; BANKR_KEY ... "API key for automatic tx submission"; OPENCLAW_HOOK_TOKEN ... "Required if running ast-watcher.sh"
Recommendation

Use narrowly scoped keys where possible, store them securely, and only set BANKR_KEY or OPENCLAW_HOOK_TOKEN in environments that need them.

What this means

If installed in cron, the skill can continue waking the agent after the initial task, which may be surprising if the user expected only manual operation.

Why it was flagged

The watcher is a persistent, cron-oriented script that can wake the local agent when pending events are detected.

Skill content
# Runs via system crontab ... "wakeMode": "now", "deliver": true
Recommendation

Install the watcher only if ongoing monitoring is desired, document the cron entry, and remove or disable it when no longer needed.

What this means

A user following the manual install path relies on the remote files served at install time.

Why it was flagged

SKILL.md documents a user-directed remote curl installation path without integrity pinning; this is not automatic, but users should notice it.

Skill content
curl -s https://agenticstreet.ai/skill.md > ~/.agentic-street/skills/agentic-street/SKILL.md
Recommendation

Prefer the registry install path when possible, or verify the source and file contents before installing remote-downloaded skill files.