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 orth command-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 scrapegraph tool. 1. Ingestion points: Data from website URLs scraped via scrapegraph in SKILL.md. 2. Boundary markers: Absent. 3. Capability inventory: The agent has shell execution capabilities (orth) and processes external text. 4. Sanitization: Absent.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 29, 2026, 05:57 PM