metodologias-de-aprendizaje
Warn
Audited by Snyk on Nov 14, 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 required workflow reads the user's request, project files, and bundled references, and its only retrieval instructions point to official provider documentation (first-party) or to generically "consulting a suitable, verified source" in a decision example, which could mean an agent-driven web lookup of outsider-authored pages.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (medium risk: 0.30). The decisive dependency is the instructed Skills CLI install from the author's individually owned GitHub repository
siberius/learning-methodologies, which supplies the skill material the agent adopts; that individual-owned repo is unofficial but canonical for the author's project with no concrete warning signs, so it is common/reputable unofficial (medium), while the static reference links are citations only.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata