brand-intake
Pass
Audited by Gen Agent Trust Hub on Mar 25, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to Indirect Prompt Injection because it ingests and processes untrusted data from external websites.
- Ingestion points: The skill uses
web_searchandweb_fetchtools in Phase 2 to retrieve content from brand websites, competitor sites, and reviews. - Boundary markers: The instructions do not define clear delimiters or provide explicit warnings to the agent to ignore instructions embedded within the retrieved web content.
- Capability inventory: The skill utilizes
web_search,web_fetch, and file-writing capabilities (creatingbrand-context-[brandname].md). - Sanitization: There is no evidence of sanitization, filtering, or validation of the external content before it is interpolated into the final output document or processed by the agent.
Audit Metadata