company-intel
Pass
Audited by Gen Agent Trust Hub on Aug 12, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it retrieves and processes content from external web sources such as news articles, corporate reports, and job boards that could contain adversarial instructions. * Ingestion points: Web search results gathered during the research phase (SKILL.md, Step 2). * Boundary markers: The skill does not define clear boundaries or 'ignore' instructions for the data it fetches from the web. * Capability inventory: The agent has the ability to perform web searches and pass its structured output to several downstream skills like positioning-statement and pestel-analysis. * Sanitization: There is no evidence of sanitization or filtering applied to the retrieved external content before it is processed.
- [EXTERNAL_DOWNLOADS]: The skill frequently performs web searches across various external domains to collect research data for analysis.
Audit Metadata