market-analyst
Pass
Audited by Gen Agent Trust Hub on Jul 12, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill instructs the agent to analyze untrusted data from external sources such as forums, store reviews, and social media comments. This activity creates a surface for indirect prompt injection where malicious instructions embedded in web content could attempt to influence the agent's behavior.
- Ingestion points: Step 2 of the workflow in
SKILL.mddirects the agent to analyze external reviews and comments. - Boundary markers: The skill lacks explicit delimiters or instructions for the agent to ignore commands that may be found within the ingested web content.
- Capability inventory: The skill uses web search tools but does not have access to sensitive capabilities like file writing, system commands, or code execution.
- Sanitization: There are no specified mechanisms for filtering or sanitizing the retrieved external text before processing.
Audit Metadata