whatisxlistening.to

AdvisoryAudited by Static analysis on May 10, 2026.

Overview

Detected: suspicious.exposed_secret_literal

Findings (1)

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.

ConcernHigh Confidence

ASI04: Agentic Supply Chain Vulnerabilities

What this means

A user installing a music dashboard could unintentionally receive unrelated agent behavior, scripts, and documentation with much broader authority.

Why it was flagged

The top-level artifact for the evaluated skill is a workspace inventory, not a scoped whatisxlistening-to skill file; it shows unrelated local skills bundled or referenced in the package.

Skill content

## Local / Unpublished ... `auto-updater` ... `findmy-location` ... `second-brain` ... `self-improving-agent`

Recommendation

Repackage only the whatisxlistening-to skill files with its own current SKILL.md, and remove workspace-level files before publishing.

ConcernHigh Confidence

ASI03: Identity and Privilege Abuse

What this means

Anyone with access to the package could use these credentials to access or alter private synced notes if the service is reachable.

Why it was flagged

The artifact exposes live-looking CouchDB admin credentials for a private Obsidian/brain-sync database, unrelated to the declared Last.fm purpose.

Skill content

Admin User: `admin`
- Admin Password: `97gYy7MzaxFMvI0IuyOJ5khu`
- Database: `obsidian`

Recommendation

Remove the credentials from the package, rotate the CouchDB password immediately, and use a secret manager or environment variables instead.

ConcernHigh Confidence

ASI03: Identity and Privilege Abuse

What this means

If invoked, the agent could use a local account credential to mutate a remote knowledge store outside the user’s music-dashboard request.

Why it was flagged

This bundled script reads a local Keychain credential and can create, update, or delete remote Ensue memories, but the evaluated skill metadata declares no credentials and this is not needed for Last.fm.

Skill content

API_KEY=$(security find-generic-password -a "clawdbot" -s "ensue-api-key" -w 2>/dev/null || true) ... create_memory ... update_memory ... delete_memory

Recommendation

Remove this script from the skill package, or make it a separate clearly declared integration with explicit user approval and scoped credentials.

ConcernHigh Confidence

ASI06: Memory and Context Poisoning

What this means

Private notes or agent memory could be copied into persistent remote memory and later reused as context beyond the original task.

Why it was flagged

The script scans local Obsidian knowledge files and pushes selected note contents into a remote embedded memory service; this broad persistent knowledge sync is unrelated to Last.fm.

Skill content

find "$OBSIDIAN_VAULT/Knowledge" -name "*.md" -type f ... grep -q "ensue_sync: *true" ... create_memory ... "embed":true

Recommendation

Exclude memory-sync code from this skill, and require explicit path limits, approval, retention rules, and clear disclosure for any knowledge-base synchronization.

ConcernHigh Confidence

ASI10: Rogue Agents

What this means

A background job could change installed agent code and skills without per-update review, affecting future behavior across tasks.

Why it was flagged

The package includes instructions for persistent autonomous updates of the agent and all installed skills, which is outside the stated Last.fm dashboard purpose.

Skill content

This skill sets up a daily cron job that: ... Updates Clawdbot itself ... Updates all installed skills (via `clawdhub update --all`)

Recommendation

Do not bundle auto-update behavior with this skill; make it a separate opt-in skill with dry-run review and clear rollback guidance.

ConcernHigh Confidence

ASI02: Tool Misuse and Exploitation

What this means

If set up, any local process or agent able to call localhost:9090 could click or type into applications on the user’s Mac.

Why it was flagged

The documentation provides a local HTTP API for UI clicks and keystrokes with Accessibility privileges; this is powerful system automation and unrelated to a Last.fm dashboard.

Skill content

server:setPort(9090) ... path == "/type" ... hs.eventtap.keyStrokes(data.text) ... path == "/key" ... hs.eventtap.keyStroke(data.modifiers or {}, data.key)

Recommendation

Do not install or enable this UI automation as part of the Last.fm skill; if needed separately, add authentication, narrow commands, and require user approval for sensitive actions.

ConcernHigh Confidence

ASI03: Identity and Privilege Abuse

What this means

A music-dashboard install could expose the agent to contact-location workflows and Apple account context the user did not expect.

Why it was flagged

The package includes an unrelated Find My location-tracking skill that depends on Apple account access and sensitive physical-location data.

Skill content

Track shared contacts via Apple Find My with street-corner accuracy. ... iCloud account signed in on your Mac ... Location sharing enabled

Recommendation

Remove the Find My skill from this package and publish it separately with explicit privacy warnings, permission requirements, and user-directed invocation.

Findings (1)

critical

suspicious.exposed_secret_literal

Location: docs/brain-sync-architecture.md:39
Finding: File appears to expose a hardcoded API secret or token.