public-support
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from external sources (e.g., website footers, contact pages, and legal notices) to identify and update contact information, creating an attack surface for indirect prompt injection.
- Ingestion points: Public website content, metadata, and link targets are read into the agent's context (SKILL.md, Inspect section).
- Boundary markers: There are no explicit instructions for using delimiters or boundary markers to isolate external content from the agent's instructions.
- Capability inventory: The skill is capable of modifying site files to update links, add contact routes, and change legal notice content (SKILL.md, May change section).
- Sanitization: No explicit sanitization or input validation is required for data read from pages before it is used to perform file modifications.
Audit Metadata