appraise
Pass
Audited by Gen Agent Trust Hub on Mar 15, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: Indirect Prompt Injection Surface
- Ingestion points: Marketplace capability descriptions and metadata retrieved from external providers (SKILL.md).
- Boundary markers: Absent; the skill does not utilize explicit delimiters to isolate untrusted provider data from the scoring logic.
- Capability inventory: Marketplace transactional and administrative commands including
openstall discover,openstall capability,openstall rate, andopenstall dispute(SKILL.md). - Sanitization: Absent; the skill lacks explicit validation or sanitization routines for content provided by marketplace sellers.
- [COMMAND_EXECUTION]: Marketplace CLI Interaction
- The skill utilizes the
openstallCLI suite to interact with the marketplace environment. These commands are consistent with the vendor's own ecosystem and are used to facilitate the appraisal and purchase processes described in the skill.
Audit Metadata