web-scraping
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill fetches HTML content from external, untrusted URLs, which creates a surface for indirect prompt injection attacks.
- Ingestion points: Web pages fetched via URLs (SKILL.md).
- Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present.
- Capability inventory: The skill utilizes network fetching and data parsing capabilities (SKILL.md).
- Sanitization: No sanitization or filtering of the fetched HTML is mentioned to prevent instructions in the data from influencing the agent's behavior.
Audit Metadata