company-intel
Pass
Audited by Gen Agent Trust Hub on Mar 29, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
orthcommand-line tool to query company intelligence APIs (brand-dev,fiber,scrapegraph). This is consistent with the skill's stated purpose of generating reports. - [PROMPT_INJECTION]: The skill identifies an indirect prompt injection surface as it ingests untrusted content from external websites via the
scrapegraphtool. 1. Ingestion points: Data from website URLs scraped viascrapegraphinSKILL.md. 2. Boundary markers: Absent. 3. Capability inventory: The agent has shell execution capabilities (orth) and processes external text. 4. Sanitization: Absent.
Audit Metadata