skills/pachca/openapi/pachca-users/Gen Agent Trust Hub

pachca-users

Pass

Audited by Gen Agent Trust Hub on Apr 8, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes shell commands using the '@pachca/cli' tool to perform administrative actions such as user creation, deletion, and status updates.
  • [EXTERNAL_DOWNLOADS]: The skill uses npx to download and execute the vendor's '@pachca/cli' package from the official NPM registry.
  • [PROMPT_INJECTION]: The skill processes employee-generated content (names, emails, status messages) retrieved from the Pachca API, which creates a potential indirect prompt injection surface.
  • Ingestion points: Employee data is retrieved using 'pachca users list' and 'pachca users get' as specified in SKILL.md.
  • Boundary markers: No explicit delimiters or instructions are used to isolate untrusted data from the agent's context.
  • Capability inventory: The skill is granted access to the Bash tool for command execution.
  • Sanitization: No data sanitization or validation mechanisms are described for the retrieved API data.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 8, 2026, 01:56 AM
Security Audit — agent-trust-hub — pachca-users