wikipedia-search
Warn
Audited by Snyk on Apr 6, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The skill's script and SKILL.md explicitly fetch and return live content from the public, user-edited Wikipedia API (see scripts/wiki.py using https://{lang}.wikipedia.org/w/api.php and the SKILL.md "Usage"/"Workflow" sections), so untrusted, user-generated pages are ingested and can directly influence the agent's outputs and actions.
MEDIUM W013: Attempt to modify system services in skill instructions.
- Attempt to modify system services in skill instructions detected (high risk: 0.70). The skill instructs automatic installation of dependencies (using pip via sys.executable) and even recommends the --break-system-packages flag and global installs, which can modify system-wide packages and bypass package-manager protections, so it pushes changes to the host system state.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W013
MEDIUMAttempt to modify system services in skill instructions.
Audit Metadata