skill-construction

Warn

Audited by Snyk on Jun 15, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (medium risk: 0.65). The required runtime inputs (extracted_components and synthesis_output) are produced by upstream agents from outsider-authored text (e.g., methodology docs/issues/PRs/web pages) and are then embedded into the constructed SKILL.md/resource files as readable prose, which the calling agent subsequently feeds into the LLM context—so this workflow can propagate outsider free text via those fields.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jun 15, 2026, 11:30 AM
Issues
1
Security Audit — snyk — skill-construction