monetization-research
Pass
Audited by Gen Agent Trust Hub on Nov 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external, third-party sources (YouTube video descriptions, sponsor links, and peer offer pages) that are not controlled by the user or the skill author.
- Ingestion points: The workflow explicitly instructs the agent to read channel descriptions and open peers' actual offer links (
SKILL.md). - Boundary markers: There are no explicit instructions or delimiters defined to isolate the external content from the agent's internal instructions or to warn the agent to ignore instructions embedded in the external data.
- Capability inventory: The skill primarily generates a research report in markdown format. It does not appear to utilize dangerous capabilities like local file writes, arbitrary command execution, or network exfiltration of sensitive local data.
- Sanitization: No sanitization or validation logic is specified for the external text before it is processed by the agent context.
Audit Metadata