skill-search
Warn
Audited by Snyk on Feb 15, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). This skill queries and parses results from public marketplaces (e.g., the skills.sh API at https://skills.sh/api/search and ctx7-indexed repos via npx ctx7), which are untrusted, user-contributed third-party listings that the agent ingests and displays as part of its workflow, enabling indirect prompt injection.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.80). The skill issues a runtime fetch to the skills.sh API (curl "https://skills.sh/api/search?q=") whose JSON "topSource" values are then used to drive npx install commands (npx skills add --all), meaning remote content directly determines which external packages/repos are installed/executed at runtime.
Audit Metadata