marketing-demand-acquisition
Pass
Audited by Gen Agent Trust Hub on Aug 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill instructions and associated Python script do not contain any malicious patterns. The Python script is a simple mathematical utility using standard libraries, and the markdown files contain professional marketing documentation and templates.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a potential attack surface due to the ingestion of external data.
- Ingestion points: Competitive domain scanning and web browsing via the BrowserOS interface as described in the SKILL.md protocols.
- Boundary markers: The skill includes explicit security protocols in SKILL.md that instruct the agent to treat external web content as hostile and verify framework versions.
- Capability inventory: The agent has capabilities for command execution via the 'rtk' ExecutionProxy and file operations via the MemoryStore interface.
- Sanitization: Global protocols in SKILL.md require the redaction of secrets and PII from context shared with subagents when processing untrusted inputs.
Audit Metadata