affiliate-blog-builder
Pass
Audited by Gen Agent Trust Hub on Mar 20, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through its web research workflow.
- Ingestion points: The workflow in SKILL.md (Step 1, Step 2, and Error Handling) directs the agent to use web_search and web_browse to fetch data from the internet about products and competitors.
- Boundary markers: No delimiters or specific instructions exist to ignore potentially malicious directions embedded within the fetched web content.
- Capability inventory: The agent utilizes web_search and web_browse tools but lacks high-risk capabilities like code execution or file-system writing.
- Sanitization: The skill does not implement any validation or sanitization of information retrieved from external websites before it is incorporated into generated articles.
Audit Metadata