agent-skill

Warn

Audited by Snyk on Nov 21, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (low risk: 0.10). The npx-skills route runs read-only find, list, and upstream verification against public community skill registries and GitHub repos, which outsiders can publish to, but the agent must actively search for them, so this is low exposure under the search-results rule.

MEDIUM W013: Attempt to modify system services in skill instructions.

  • Attempt to modify system services in skill instructions detected (low risk: 0.10). The npx-skills workflow can install, update, remove, and sync agent skills and edit agents/*/package.json and global/package.json, which changes the supporting agent environment, but no explicit irreversible operational loss is established, so it fails gate 2 and stays at low.

Issues (2)

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

W013
MEDIUM

Attempt to modify system services in skill instructions.

Audit Metadata
Risk Level
MEDIUM
Analyzed
Nov 21, 2026, 04:19 PM
Issues
2