influencer-discovery
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues detected. The skill is entirely instructional and guides the agent through a manual research workflow using the agent's native search and reasoning capabilities.
- [INDIRECT_PROMPT_INJECTION]: The skill involves ingesting untrusted data from external platforms (YouTube, X, blogs) during the discovery phase (Step 3-7). However, because the skill's capabilities are restricted to information synthesis and reporting within the agent's response, and it lacks dangerous capabilities like file-system writes or shell execution, the vulnerability surface for executing malicious instructions embedded in web content is minimal. Boundary markers and sanitization are not explicitly defined, but the intended output is a structured report.
Audit Metadata