pricing
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a vulnerability surface for indirect prompt injection due to its core functionality of auditing external pricing content.
- Ingestion points: The skill instructions in
SKILL.mdandreferences/pricing-page-teardown.mddirect the agent to fetch and analyze data from external URLs or pasted text from pricing pages (referred to as the "paste test"). - Boundary markers: The instructions do not define explicit delimiters or instructions for the agent to ignore or isolate commands embedded within the external page content being audited.
- Capability inventory: The skill is entirely text-based (Markdown) and does not include any scripts, tools, or executables. It lacks capabilities for local file system access, arbitrary shell command execution, or network operations beyond the initial page fetch.
- Sanitization: There is no logic defined for validating or filtering content from the external sources before it is processed by the agent.
Audit Metadata