market-research
Pass
Audited by Gen Agent Trust Hub on Jul 12, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill consists entirely of markdown instructions (agent-guide). No scripts, binaries, or configuration files are present.- [NO_CODE]: There are no executable files or code blocks within the skill. No code was found in the analyzed file.- [PROMPT_INJECTION]: The skill instructs the agent to process untrusted external data such as product reviews, social media, and competitor websites. This constitutes an attack surface for indirect prompt injection. However, the instructions mandate building an 'evidence ladder' and grading confidence, which encourages the agent to treat external content as data to be analyzed rather than instructions to be executed.
Audit Metadata