competitor-site-analysis
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill fetches content from up to 6 pages of external websites provided by the user and instructs the agent to extract structured data. This creates a surface for indirect prompt injection where an attacker-controlled website could include malicious instructions designed to influence the agent's behavior or output.
- Ingestion points: External website content fetched during Step 3 (SKILL.md).
- Boundary markers: Absent. The instructions do not specify the use of delimiters or warnings to ignore instructions embedded in the website content.
- Capability inventory: The skill utilizes network access to fetch website data and Playwright MCP for rendering JavaScript content.
- Sanitization: Absent. The skill does not describe any methods for filtering or sanitizing the retrieved website content before processing.
Audit Metadata