eeat-audit
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to fetch and analyze external URLs provided by the user. It lacks boundary markers or specific instructions to treat this external content as untrusted, creating a surface for indirect prompt injection attacks where malicious instructions on a webpage could influence the agent's behavior.
- Ingestion points: The agent fetches external content from user-provided URLs as instructed in the 'Step 1: Read the Page' section of
SKILL.md. - Boundary markers: There are no defined delimiters or 'ignore' instructions provided to the agent to separate the fetched content from the skill's own logic.
- Capability inventory: The skill utilizes page fetching and content analysis capabilities to generate scores and recommendations.
- Sanitization: No sanitization or validation of the fetched content is specified before it is processed by the agent.
Audit Metadata