industry-landscape
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from diverse external sources (LinkedIn, Google News, academic research, etc.), which establishes an attack surface for indirect prompt injection. A malicious actor could embed instructions in search results to influence the agent. However, the risk is negligible as the skill lacks high-privilege tools (e.g., file writing or shell access) and is constrained by read-only guidelines.
- Ingestion points: External data is ingested via search tools such as apollo_company_search, akta_industry_search, exa_search, scholar_search_mixed, linkedin_web_v2_search_jobs, and google_news_bulk_articles.
- Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands in the ingested data.
- Capability inventory: The skill is limited to information retrieval and synthesis; it contains no subprocess calls, file-system writes, or network exfiltration operations.
- Sanitization: No input sanitization or output filtering is specified for the processed content.
Audit Metadata