linkbuilding

Pass

Audited by Gen Agent Trust Hub on Apr 19, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) because it retrieves and processes content from external domains to perform phase assessments. If a target website contains hidden instructions, they could potentially influence the agent's reasoning or tactic selection.
  • Ingestion points: The agent fetches the homepage of the user-provided domain and analyzes Google search results (SKILL.md).
  • Boundary markers: The skill does not provide explicit delimiters or instructions to ignore embedded agent commands when reading external site content.
  • Capability inventory: The agent uses web browsing and search tools to assess content volume and brand presence.
  • Sanitization: No sanitization or filtering of retrieved HTML content is specified before the agent processes the information.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 19, 2026, 09:22 AM