blindspot
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources to map unknown areas for the user, which creates a potential surface for indirect prompt injection if those sources contain malicious instructions.\n
- Ingestion points: The skill uses the
WebSearchtool to retrieve information about pitfalls and common mistakes from the internet and thefind-docstool to scan repository-based documentation.\n - Boundary markers: The instructions do not define specific delimiters or instructions for the agent to distinguish between its own logic and potentially malicious content embedded in the search results or documentation.\n
- Capability inventory: The skill utilizes
WebSearchfor external data retrieval,AskUserQuestionfor user interaction, and repository exploration tools to analyze the codebase environment.\n - Sanitization: The skill lacks explicit steps for sanitizing, filtering, or validating external content before it is processed or presented to the user.
Audit Metadata