competitor-profiling
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to ingest and synthesize data from external, untrusted sources such as competitor websites, LinkedIn profiles, and third-party review sites.
- Ingestion points: The agent is directed to read homepage headlines, 'About' pages, customer testimonials, and reviews from sites like G2 and Trustpilot (SKILL.md).
- Boundary markers: The instructions do not define clear delimiters or specific warnings to the agent to disregard potentially malicious instructions embedded in the external content it fetches.
- Capability inventory: This skill is purely instructional and does not include scripts for subprocess execution, file writes, or network operations, relying instead on the platform's native web-access tools.
- Sanitization: There are no specified mechanisms to sanitize or validate the external text before it is processed by the agent.
Audit Metadata