site-history
Pass
Audited by Gen Agent Trust Hub on Aug 14, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill ingests untrusted data from web searches, creating a surface for indirect prompt injection.\n
- Ingestion points: The skill uses WebSearch and WebFetch tools to retrieve data from the internet as described in the 'Research Workflow' section of SKILL.md.\n
- Boundary markers: No explicit delimiters or ignore-instructions are defined to protect the agent from potentially malicious commands embedded in search results.\n
- Capability inventory: The skill environment permits access to tools like Bash, Write, and Edit.\n
- Sanitization: The instructions do not specify any validation or sanitization of the retrieved data before it is processed into the final report.
Audit Metadata