psp-construct
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill utilizes the
WebFetchtool to gather vocabulary and industry insights from third-party sources such as job boards and social media. This behavior introduces a vulnerability surface where adversarial instructions placed in those external sources could potentially influence the agent's behavior or output during the vocabulary mining process.
Audit Metadata