signup-flow-cro
Pass
Audited by Gen Agent Trust Hub on Apr 11, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill instructs the agent to ingest external data from a local context file, creating a surface for indirect prompt injection.
- Ingestion points: The skill specifies reading context from
.claude/product-marketing-context.mdbefore proceeding with the task. - Boundary markers: Absent. There are no instructions provided to the agent to treat the file content as untrusted or to ignore instructions embedded within it.
- Capability inventory: None. The skill is purely conversational/consultative and does not possess capabilities for shell execution, network access, or file system modifications.
- Sanitization: Absent. The content of the context file is processed as natural language without validation or escaping.
Audit Metadata