prospect-research-compiler
Pass
Audited by Gen Agent Trust Hub on Aug 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill aggregates intelligence from external, untrusted sources such as news, social media, and third-party websites. This creates an attack surface for indirect prompt injection, where malicious instructions embedded in these sources could attempt to subvert the agent's behavior.
- Ingestion points: Intelligence gathered from news, social media, and websites as described in SKILL.md.
- Boundary markers: Absent. There are no instructions for the agent to distinguish between data and instructions when processing external content.
- Capability inventory: The skill uses the agent's default tools to read and aggregate data. No specific execution tools are defined in this skill.
- Sanitization: Absent. There is no mechanism described for filtering or sanitizing the content fetched from the web.
Audit Metadata