Caveat verdict

auto-reply

88
🟢 Trusted
No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.

Monitors Instagram DMs and auto-replies using the user's own authenticated session via local API; includes explicit prompt-injection detection (SECURITY_PATTERNS) to reject malicious message content.

⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.

Automated static analysis — not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.

58
security
90
transparency
70
maintenance

Findings (8)

Pattern match medium

References sudo — requests elevated privileges

scripts/auto-reply.js · prose · downgraded · sudo

Pattern match medium

References child_process — can spawn system processes

scripts/auto-reply.js · prose · downgraded · child_process

Pattern match medium

HTTP request to bare IP address — common in malicious payloads

scripts/check-notify.js · prose · downgraded · http://127.0.0.1

Pattern match low

Opens WebSocket connection

scripts/check-notify.js · prose · downgraded · WebSocket

Pattern match low

Node http/https module — low-level network access

scripts/check-notify.js · prose · downgraded · require('http')

Pattern match low

Uses XMLHttpRequest — network access

scripts/check-notify.js · prose · downgraded · XMLHttpRequest

Pattern match low

References webhook/callback URL

scripts/dm-watcher.js · prose · downgraded · WEBHOOK_URL

Pattern match low

Accesses sensitive environment variables

scripts/dm-watcher.js · prose · downgraded · process.env.DISCORD_TOKEN

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class D). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.

Permissions & capabilities

No declared permissions — minimal attack surface.

Is this flag fair?

Check another skill Browse the registry Auditing your own skills or configs? Use the API