funnel-audit
Pass
Audited by Gen Agent Trust Hub on Jun 29, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill follows its stated purpose of auditing sales funnels for conversion rate optimization. It does not perform any suspicious network operations, credential harvesting, or unauthorized file access.
- [PROMPT_INJECTION]: The skill ingests untrusted data from
funnel_descriptionandfunnel_url. While this creates an indirect prompt injection surface, it is necessary for the skill's primary function. - Ingestion points: External content from
funnel_urland user-providedfunnel_descriptionin SKILL.md. - Boundary markers: None present; the agent is instructed to directly evaluate the content observed at the URL.
- Capability inventory: The skill directs the agent to identify steps and score content based on observations, but does not invoke administrative shell commands or file-writing operations.
- Sanitization: No explicit sanitization or instruction-ignoring delimiters are defined for the external input.
Audit Metadata