lead-research-assistant
Pass
Audited by Gen Agent Trust Hub on Apr 7, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes untrusted data from external search results and the user's local codebase without implementing boundary markers or sanitization. An attacker who controls a website indexed by the agent or who places malicious comments in a codebase could theoretically influence the agent's behavior.
- Ingestion points: The local repository files (when run from a codebase) and external web content (job postings, company websites, and tech stack signals).
- Boundary markers: None identified. The instructions do not use delimiters or explicit 'ignore embedded instructions' warnings for the data being analyzed.
- Capability inventory: The skill utilizes file system read access to analyze the codebase and web search capabilities to identify leads.
- Sanitization: No validation or escaping of external content is described before the information is used to generate outreach strategies.
Audit Metadata