frame-recon
Pass
Audited by Gen Agent Trust Hub on Jul 9, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill utilizes
WebSearchandWebFetchtools to retrieve regulatory guidance and information from external web sources. - [COMMAND_EXECUTION]: The skill is configured with access to the
Bashtool in its frontmatter, though no specific shell commands are invoked within the provided instructions. - [PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection as it processes both project documents and external web content without isolation protocols.
- Ingestion points: Corporate documents (articles, bylaws, cap tables) read from the project and external data retrieved via
WebSearchandWebFetch. - Boundary markers: The instructions do not define explicit delimiters or instructions to ignore embedded commands within the analyzed documents.
- Capability inventory: Access to
Bash,Write,Read,Glob,Grep, andWebFetchtools. - Sanitization: No content validation or sanitization steps are defined for the ingested data.
Audit Metadata