researcher
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill directs the agent to gather and analyze data from various untrusted external sources which could contain malicious instructions. 1. Ingestion points: Competitor websites, hero sections, user reviews, forums, and social media posts (SKILL.md). 2. Boundary markers: Absent; no delimiters or warnings are provided to prevent the agent from obeying instructions embedded in the external data. 3. Capability inventory: Implied web browsing and content extraction tools required to fulfill research deliverables. 4. Sanitization: Absent; the skill lacks validation or filtering logic for the data it collects.
Audit Metadata