orchestrating-search-visibility
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill file is composed entirely of markdown instructions and does not include any code, shell commands, or automated network requests. No malicious patterns such as obfuscation or credential theft were detected.\n- [INDIRECT_PROMPT_INJECTION]: The skill creates a surface for indirect prompt injection by instructing the agent to analyze external URLs provided by the user, though this is necessary for its primary function.\n
- Ingestion points: The Discovery Questions in SKILL.md prompt the user for the full URL of the primary content piece and competitor websites.\n
- Boundary markers: The instructions do not include specific delimiters or warnings to the agent to ignore instructions that might be embedded in the retrieved content.\n
- Capability inventory: The skill itself does not have scripts or tools; it relies on the agent's native browsing capabilities to fetch data.\n
- Sanitization: No explicit sanitization or content validation steps are defined for the data retrieved from the user-provided URLs.
Audit Metadata