improve-search-visibility-entity-footprint
Pass
Audited by Gen Agent Trust Hub on Nov 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes content from external public profile pages and local markdown files, which presents a risk of indirect prompt injection if those sources contain malicious instructions.
- Ingestion points: The skill reads a local reference file
../improve-search-visibility/references/entity-and-local.mdand fetches data from external public profile pages. - Boundary markers: There are no instructions defining boundary markers or explicit commands for the agent to ignore instructions embedded within the fetched external data.
- Capability inventory: The skill is capable of performing network fetches and writing corrected entity tables and fix candidates.
- Sanitization: The instructions do not specify any sanitization, validation, or escaping of the content retrieved from external sources before it is processed by the agent.
Audit Metadata