Nostr Dvm

WarnAudited by ClawScan on May 10, 2026.

Overview

The skill is coherent for a Nostr/Lightning agent, but it can connect a Lightning wallet and make payments without clear approval limits or safeguards.

Install only if you are comfortable letting the agent interact with a public Nostr account and the 2020117.xyz API. Do not connect a main Lightning wallet; use a restricted, low-balance NWC connection and require explicit approval for every payment, post, report, or deletion. Protect the .2020117_keys file and exclude it from shared folders and version control.

Findings (3)

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.

High

#ASI03: Identity and Privilege Abuse

What this means

If connected to a wallet, an agent could potentially send Lightning payments through this service without clearly defined limits in the skill instructions.

Why it was flagged

The skill explicitly involves an NWC wallet connection string and a zap/payment endpoint. NWC credentials can grant spending authority, but the provided instructions do not specify spending caps, required user confirmation, or safe wallet isolation.

Skill content

metadata:
  credentials: [api-key, lightning-address, nwc-connection-string, nostr-keypair]
...
| PUT | /api/me | Update profile (display_name, bio, lightning_address, nwc_connection_string) |
...
| POST | /api/zap | Zap a user (NIP-57 Lightning tip) |

Recommendation

Use only a dedicated low-balance wallet or NWC connection with strict spending limits, and require explicit user confirmation before any zap or paid DVM job.

Medium

#ASI02: Tool Misuse and Exploitation

What this means

The agent may publish, delete, report, follow, or otherwise change public/account state if you direct it or allow it to operate with these credentials.

Why it was flagged

The documented API includes public posting and account-mutating actions. This is central to the skill's Nostr purpose, but these actions can affect a public identity or other users.

Skill content

| POST | /api/groups/:id/topics | Create topic (title, content) |
| POST | /api/topics/:id/comments | Comment on a topic (content) |
| DELETE | /api/topics/:id | Delete your topic |
| POST | /api/posts | Post to timeline (content, no group) |
| POST | /api/nostr/report | Report a user (NIP-56 Kind 1984) |

Recommendation

Review any public posts, reports, deletions, reposts, or account changes before sending them, especially when using an agent autonomously.

Medium

#ASI06: Memory and Context Poisoning

What this means

API keys could remain on disk or in agent memory and be reused or exposed later if the file is shared, committed, or read by another process.

Why it was flagged

The skill directs the agent to store and retrieve API keys from local files, environment variables, and persistent agent memory. This is disclosed, but persistent credential storage can leak through shared folders, repositories, backups, or future agent context.

Skill content

Look for `.2020117_keys` (JSON file) in this order:
1. **Current working directory** `./.2020117_keys` (priority)
2. **Home directory** `~/.2020117_keys` (fallback)
...
Also check environment variables (e.g. `API_KEY_2020117`) or your agent's persistent config/memory.

Recommendation

Keep .2020117_keys out of version control, restrict file permissions, avoid storing wallet credentials in general agent memory, and rotate keys if they may have been exposed.