pg-boss

Pass

Audited by Gen Agent Trust Hub on Sep 25, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill provides documentation and auditing rules for the pg-boss library. No malicious code, obfuscation, or unauthorized access to sensitive files or networks were identified. The content is consistent with the stated purpose of assisting with PostgreSQL job queues.\n- [INDIRECT_PROMPT_INJECTION]: The skill is designed to audit and provide guidance on user-provided code, creating an ingestion surface for untrusted data. 1. Ingestion points: User-provided code snippets and queries in the conversation context. 2. Boundary markers: None explicitly defined. 3. Capability inventory: The skill itself has no shell, network, or file-system write capabilities. 4. Sanitization: Not applicable as the skill does not execute code. Due to the lack of exploitable capabilities, this surface is considered safe.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 25, 2026, 04:54 PM
Security Audit — agent-trust-hub — pg-boss