Nostr Nak
Analysis
This is a coherent Nostr CLI helper, but it can use a full Nostr private key to post as the user without declared credential requirements or explicit approval limits.
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.
Checks for instructions or behavior that redirect the agent, misuse tools, execute unexpected code, cascade across systems, exploit user trust, or continue outside the intended task.
**Always** wrap `nak` commands in `script` to force a pseudo-TTY: `script -q -c "nak req ..." /dev/null | cat`
The skill directs the agent to run local CLI commands through a PTY wrapper. This is central to the skill's purpose, but it is still broad local command execution that users should review for high-impact commands such as posting.
Required binaries (all must exist): none ... No install spec — this is an instruction-only skill.
The metadata does not declare the `nak` or `script` binaries even though the skill instructions require them, so users must rely on whatever local binaries are already installed.
Checks whether tool use, credentials, dependencies, identity, account access, or inter-agent boundaries are broader than the stated purpose.
**Posting**: Use `nsec...` or hex private key with the `--sec` flag.
This tells the agent to use a full Nostr private key for posting. The registry metadata declares no primary credential or required environment variable, and the instructions do not bound when this signing authority should be used.
