icp-deep-dive
Pass
Audited by Gen Agent Trust Hub on Aug 12, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits a potential surface for indirect prompt injection by processing external data from the web and user inputs without explicit sanitization or boundary markers.\n
- Ingestion points: The skill collects information from external websites using the
firecrawl_agenttool and processes user-supplied content such as customer reviews, surveys, and chat logs in Step 3.\n - Boundary markers: There are no explicit delimiters or instructions provided to the agent to disregard potentially malicious instructions embedded within the ingested data.\n
- Capability inventory: The skill has permissions to read brand foundation files and write synthesized results to the local filesystem (e.g.,
./brand/brand-dna.mdand./brand/icp-cards.md).\n - Sanitization: The skill does not describe any methods for escaping or filtering the content retrieved from external sources before it is used to generate the final persona cards.
Audit Metadata