offer-ladder
Pass
Audited by Gen Agent Trust Hub on Nov 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function involves processing data from untrusted external sources, creating a potential attack surface.
- Ingestion points: The skill explicitly requires a client website URL and uses tools like WebFetch, Apify, and the Google Drive connector to pull service lines, capabilities, and case studies into the agent context in Phase 1.
- Boundary markers: The instructions lack explicit boundary markers or directions for the agent to ignore instructions that might be embedded within the scraped website content or documents.
- Capability inventory: The skill is focused on analytical reasoning and strategy generation. It does not appear to use the ingested data to trigger high-risk actions such as system command execution, file system modifications, or network exfiltration to unknown domains.
- Sanitization: There is no mention of sanitizing or validating the retrieved content to prevent malicious instructions from influencing the agent's behavior.
Audit Metadata