market-sizing-analysis
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions in
SKILL.mdandreferences/sandbase-api-map.mddirect the agent to use search tools (tavily_search,exa_search) to gather market evidence from external websites. This ingested data is incorporated into the agent's context without the use of explicit boundary markers or sanitization instructions, creating a surface where malicious instructions embedded in third-party web content could influence the agent's calculations or subsequent tool calls. Ingestion points:references/sandbase-api-map.md(viatavily_searchandexa_search). Boundary markers: Absent. Capability inventory:sandbase_call_tool(network operations). Sanitization: Absent. - [NO_CODE]: The skill package is composed entirely of markdown documentation and reference materials; it does not include any executable scripts, binaries, or automated installation manifests.
Audit Metadata