product-frameworks
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface due to its reliance on external data ingestion.\n
- Ingestion points: Data enters the agent's context through
WebFetch,WebSearch, andghCLI search commands as described inrules/market-competitive.mdandreferences/competitive-analysis-guide.md.\n - Boundary markers: No explicit delimiters are provided in the skill instructions to partition external content from the agent's internal logic.\n
- Capability inventory: The skill is limited to
Read,Glob,Grep,WebFetch, andWebSearch, which restricts the potential impact of data poisoning attacks.\n - Sanitization: External inputs are not sanitized or filtered before being processed by the agent.\n- [COMMAND_EXECUTION]: The skill includes pre-defined GitHub CLI (
gh) commands for repository research and market analysis, which are standard for the tool's documented use cases.
Audit Metadata