search-engine-marketing-sem
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill establishes a workflow that involves ingesting and analyzing content from user-provided URLs.
- Ingestion points:
SKILL.mdasks the user to provide website and landing page URLs in Discovery Question 6. - Boundary markers: The instructions lack specific delimiters or warnings to the agent to ignore instructions that might be embedded in the external landing page content during the review phase.
- Capability inventory: The skill's workflow includes a 'Landing Page Review' step, which implies the use of tools to fetch or read external web content, creating an attack surface for instructions hosted on those sites.
- Sanitization: There are no instructions for sanitizing or filtering data retrieved from the provided URLs before processing it.
- [NO_CODE]: The skill consists entirely of markdown instructions and metadata, with no accompanying scripts, executables, or package dependencies.
Audit Metadata