how-to-survey
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill requires the agent to search for and fetch arbitrary external web pages to collect data and evidence.
- Ingestion points: External content is retrieved using web search and fetch tools as described in
references/web-research.md. - Boundary markers: The instructions do not define specific delimiters or security instructions to prevent the agent from following malicious commands that might be embedded in the fetched web pages.
- Capability inventory: The agent has the capability to perform web searches, fetch full page content, and write structured survey notes and evidence logs to the file system.
- Sanitization: There are no provisions for sanitizing or filtering the content retrieved from external sources before it is analyzed or recorded in the survey documentation.
Audit Metadata