ads
Pass
Audited by Gen Agent Trust Hub on Jul 21, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it fetches and processes untrusted data from external landing pages.
- Ingestion points: External URLs are fetched using
playwrightandrequestsvia theanalyze_landing.pyandfetch_page.pyscripts. - Boundary markers: The instructions lack delimiters or warnings to ignore instructions found within the analyzed web content.
- Capability inventory: The agent has access to tools including
Bash,WebFetch, and file system utilities (Read,Grep,Glob), which increases the potential impact if an injection attack succeeds. - Sanitization: No sanitization or filtering is performed on the content retrieved from external sources before it is interpreted by the agent.
Audit Metadata