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 WebFetch tool 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
Risk Level
SAFE
Analyzed
Sep 8, 2026, 10:28 PM
Security Audit — agent-trust-hub — psp-construct