Caveat verdict

letundra

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

Travel information skill (visas, news, holidays, currency rates) fetching data from letundra.com; no credential requirements, and all content is read-only informational queries to a stated single source.

⚠ 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
100
transparency
80
maintenance

Findings (3)

Pattern match critical

Unicode homoglyph detected — uses lookalike characters to evade pattern matching

letundra-rss/SKILL.md · prose

Pattern match medium

Uses exec() — may execute shell commands

scripts/letundra_yandex.js · prose · downgraded · exec(

Pattern match low

Node http/https module — low-level network access

scripts/letundra_yandex.js · prose · downgraded · require('https')

Permissions & capabilities

Requires 1 system binary.

Is this flag fair?

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