market-brand
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill scrapes and processes content from external websites (Homepages, blogs, social profiles) provided by users, which creates a potential surface for indirect prompt injection attacks. \n
- Ingestion points: The skill uses the
/market brand <url>command andscripts/analyze_page.pyto ingest raw text from external URLs. \n - Boundary markers: The instructions do not include specific delimiters or warnings to the agent to ignore instructions embedded within the source material. \n
- Capability inventory: The skill invokes a local script (
scripts/analyze_page.py) and writes output to the filesystem (BRAND-VOICE.md). \n - Sanitization: There are no instructions for sanitizing, validating, or filtering the content retrieved from external sources. \n- [COMMAND_EXECUTION]: The skill instructs the agent to run a local script,
scripts/analyze_page.py, to perform data retrieval. While this is a core component of the skill's functionality, it involves executing code that interacts with arbitrary network locations.
Audit Metadata