lead-research-assistant
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions direct the agent to analyze external, untrusted content including company websites, job postings, and GitHub repositories to identify leads. This creates a vulnerability surface where an attacker could embed malicious instructions in these external sources to manipulate the agent's behavior.
- Ingestion points: Company websites, job boards, and public GitHub repositories (referenced in SKILL.md).
- Boundary markers: There are no specific instructions or delimiters provided to the agent to treat ingested external data as untrusted or to ignore embedded instructions.
- Capability inventory: The skill involves reading the local codebase and performing external searches; it does not demonstrate command execution, persistence, or data exfiltration capabilities.
- Sanitization: No sanitization or validation of external content is defined in the workflow.
Audit Metadata