market-brand
Pass
Audited by Gen Agent Trust Hub on May 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute a local script located at
scripts/analyze_page.py. This script is responsible for performing network operations to fetch content from various web pages provided by the user. - [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection due to its core functionality of processing untrusted data from the web.
- Ingestion points: Raw text is ingested from external URLs (Homepage, About page, Blog, etc.) mentioned in the
SKILL.mdinstructions. - Boundary markers: The instructions lack delimiters or explicit warnings to the agent to ignore any embedded instructions found within the fetched content.
- Capability inventory: The skill utilizes
scripts/analyze_page.pyto perform network reads and is capable of creating new files (e.g.,BRAND-VOICE.md). - Sanitization: There is no mention of sanitization or validation of the external content before it is processed by the agent.
Audit Metadata