gsd-verify-work
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user feedback during conversational UAT sessions and uses that data to drive automated diagnostic and fixing processes.
- Ingestion points: Untrusted data enters the agent context through the "conversational testing" interactions defined in the objective.
- Boundary markers: There are no explicit instructions to sanitize user input or utilize delimiters to prevent the agent from interpreting instructions embedded within user feedback.
- Capability inventory: The skill is configured with access to powerful tools including
Bash,Write,Edit, andAgentto perform fixes. - Sanitization: The process description lacks explicit validation or escaping steps for the conversational data before it is processed by the diagnostic and fix-planning logic.
Audit Metadata