skills/plurigrid/asi/pijul/Gen Agent Trust Hub

pijul

Pass

Audited by Gen Agent Trust Hub on Jun 20, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches patches and repository data from the official Pijul forge at nest.pijul.com via pijul clone and pijul pull operations.
  • [COMMAND_EXECUTION]: Instructs the agent on using standard Pijul CLI commands for patch management and repository state transitions, including pijul record, pijul fork, and pijul apply.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it ingests untrusted patch data from external repositories into the agent's context. However, this is inherent to the functionality of a version control tool and is considered a standard operational risk rather than a malicious finding.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 20, 2026, 09:01 AM
Security Audit — agent-trust-hub — pijul