competitive-platform-analysis
Pass
Audited by Gen Agent Trust Hub on Nov 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest and analyze data from various external sources including competitor websites, portfolio platforms (such as Behance, Dribbble, and Vimeo), and professional networks like LinkedIn. This activity introduces a potential surface where malicious instructions hidden in external pages could influence the agent's behavior during the analysis process.\n
- Ingestion points:
SKILL.md(Data sources section) specifies researching competitor sites, LinkedIn, Dribbble, Behance, Vimeo, and Clutch.co.\n - Boundary markers: Absent. The instructions do not define specific delimiters or guardrails to prevent the agent from following instructions potentially embedded in the researched content.\n
- Capability inventory: The skill relies on the agent's ability to browse external URLs and synthesize information from text and metadata.\n
- Sanitization: Absent. There are no instructions provided to sanitize, filter, or validate the content retrieved from these external platforms before processing.
Audit Metadata