company-intelligence
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions involve retrieving and synthesizing information from external web sources using search and scraping tools. This introduces a surface for indirect prompt injection, where an attacker could place malicious instructions on a webpage or in a job posting to influence the agent's report generation.
- Ingestion points: Information retrieved from external websites, earnings calls, and job postings via Perplexity, Exa, and Apify.
- Boundary markers: No explicit instructions are provided to the agent to treat external content as untrusted or to ignore embedded instructions within that data.
- Capability inventory: The skill uses tools for web search and data extraction. No dangerous capabilities like direct shell execution or sensitive file system access are present in the skill body.
- Sanitization: The skill does not define specific methods for sanitizing or filtering the content retrieved from external sources.
Audit Metadata