competitive-analysis
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to ingest and process untrusted external data from the open web and the GitHub API to generate competitive reports.
- Ingestion points: External data enters the agent context through the use of
WebFetch,WebSearch, andgh apicalls documented inSKILL.mdandreferences/competitive-analysis-guide.md. - Boundary markers: The skill templates (SWOT, Porter's, Competitor Profiles) do not define clear delimiters or provide instructions to the agent to disregard potential instructions embedded within the research data.
- Capability inventory: The skill utilizes network-enabled tools (
WebFetch,WebSearch,gh) to gather intelligence but does not include any scripts that perform file system modifications, arbitrary code execution, or further network transmission of collected data beyond generating the report. - Sanitization: No specific content sanitization, validation, or filtering mechanisms are defined for the data retrieved from external sources.
Audit Metadata