prospecting-research
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill methodology requires the agent to ingest and analyze data from untrusted external sources, such as LinkedIn profiles, social media posts, and news articles. This creates a surface for indirect prompt injection where an attacker could place malicious instructions in publicly accessible content that the agent is expected to process.
- Ingestion points: Step 1 (Company Research) and Step 2 (Contact Research) in SKILL.md.
- Boundary markers: Not present in instructions.
- Capability inventory: The skill provides a framework for research and message synthesis.
- Sanitization: No explicit instructions for sanitizing or escaping external content.
Audit Metadata