competitor-intel-agent
Pass
Audited by Gen Agent Trust Hub on Aug 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it fetches and processes content from external competitor websites that are not under the user's control.
- Ingestion points: Data enters the agent's context through
WebFetchandWebSearchtools as described inreferences/monitoring-dimensions.md(e.g., fetching pricing pages, blogs, and job boards). - Boundary markers: The instructions do not specify explicit delimiters or "ignore instructions" wrappers for the data returned by web tools, which could lead the agent to follow instructions embedded in a competitor's website.
- Capability inventory: The agent has access to
WriteandBashtools, meaning a successful injection could potentially lead to unauthorized file modifications or command execution. - Sanitization: There is no explicit requirement for the agent to sanitize or escape HTML/text content before processing it for analysis or report generation.
Audit Metadata