prospect-research-integration
Pass
Audited by Gen Agent Trust Hub on Mar 18, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill defines patterns for researching and enriching prospect data from external, untrusted sources (LinkedIn, News APIs, job postings). This architecture creates a surface for indirect prompt injection, where instructions embedded in the external content could manipulate the agent's reasoning or synthesis.
- Ingestion points: External data is ingested through several functions including
scrape_linkedin_profile,extract_relevant_news, andscrape_job_postingsas described inSKILL.md. - Boundary markers: The provided code logic for fetching and processing data does not demonstrate the use of delimiters or specific 'ignore embedded instructions' prompts.
- Capability inventory: The skill uses the collected data to synthesize insights (
synthesize_insights) and score profiles, which directly influences the final intelligence provided to the user. - Sanitization: There is no evidence of sanitization, escaping, or validation of the content retrieved from these external providers.
Audit Metadata