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

pachca-search

Pass

Audited by Gen Agent Trust Hub on Mar 7, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the Bash tool to run search and authentication commands using the @pachca/cli.
  • [EXTERNAL_DOWNLOADS]: The skill downloads the @pachca/cli package via npx and npm. This package is a vendor-owned resource provided by the skill author.
  • [PROMPT_INJECTION]: The skill exposes an attack surface for indirect prompt injection (Category 8). 1. Ingestion points: The agent processes data retrieved from searches of messages, chats, and employee profiles as seen in SKILL.md. 2. Boundary markers: There are no instructions to use delimiters or ignore instructions within the search data. 3. Capability inventory: The agent has Bash shell access with permissions to use npm, npx, and the pachca CLI. 4. Sanitization: No sanitization or validation of the ingested search data is specified.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 7, 2026, 04:04 PM