market-funnel
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external websites when the user invokes the funnel analysis command. This content could potentially contain malicious instructions designed to manipulate the agent's output or behavior.
- Ingestion points: Content of the website provided in the parameter of the
/market funnelcommand. - Boundary markers: There are no instructions to use delimiters or ignore instructions found within the fetched web content.
- Capability inventory: The skill reads local reference documentation and other report files (e.g.,
MARKETING-AUDIT.md) and writes analysis results toFUNNEL-ANALYSIS.md. It does not utilize shell execution or external exfiltration tools. - Sanitization: No sanitization or validation logic is defined for the content retrieved from external URLs.
Audit Metadata