competitor-intel
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes data from external web sources which could potentially contain malicious instructions intended to manipulate the agent's output or reasoning.
- Ingestion points: Web search results and external site content from third-party platforms including G2, Capterra, Trustpilot, and GitHub as specified in the 'Research Phase'.
- Boundary markers: Absent. The agent is not instructed to use delimiters or specific guidelines to distinguish external data from internal instructions.
- Capability inventory: The skill uses web search capabilities and reads local project files (specifically
FOUNDER_CONTEXT.md). It does not define capabilities for arbitrary command execution or network exfiltration. - Sanitization: No sanitization, filtering, or validation of the retrieved external content is specified before the agent processes it to identify strategies and predictions.
Audit Metadata