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
Risk Level
SAFE
Analyzed
Aug 14, 2026, 03:45 PM
Security Audit — agent-trust-hub — site-history