survey
Pass
Audited by Gen Agent Trust Hub on Mar 10, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: Indirect Prompt Injection Surface
- Ingestion points: The skill utilizes the WebFetch tool across four parallel research lanes to ingest untrusted data from external websites.
- Boundary markers: The skill instructions do not specify the use of delimiters or clear markers to separate retrieved web content from the agent's internal synthesis instructions.
- Capability inventory: The skill is granted access to the Read, Write, Bash, and WebFetch tools, allowing it to modify the local filesystem based on research findings.
- Sanitization: There is no requirement for sanitizing, escaping, or validating content retrieved from the web before it is written to the .survey/ directory or presented to the user.
Audit Metadata