free-tool-arsenal
Pass
Audited by Gen Agent Trust Hub on Mar 12, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface. Ingestion points: Untrusted content from the web accessed via WebSearch and WebFetch tools. Boundary markers: Absent; there are no instructions to differentiate between user directives and data retrieved from external sources. Capability inventory: The agent can use Read, Write, Edit, Grep, and Glob to interact with the local file system. Sanitization: No validation or filtering process is specified for external data before it is processed or written to files.
Audit Metadata