signup-flow-cro
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is entirely composed of instructional markdown and persona-defining text. It does not include any scripts (Python, Node.js, Shell), automation, or network-enabled tools.
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read context from external files such as
.agents/product-marketing-context.md. While reading external files can introduce untrusted data into the prompt, the skill lacks any dangerous capabilities (like file writing or command execution) that could be exploited via this vector. - Ingestion points: SKILL.md (reads
.agents/product-marketing-context.md). - Boundary markers: None explicitly defined in the instructions.
- Capability inventory: No executable capabilities detected.
- Sanitization: No specific sanitization or filtering instructions for the ingested content.
Audit Metadata