skills/observeinc/skills/observe-cli/Gen Agent Trust Hub

observe-cli

Pass

Audited by Gen Agent Trust Hub on Aug 18, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted data retrieved from external sources such as telemetry datasets, platform documentation, and other skills stored in Observe. This creates a surface for indirect prompt injection where malicious content in the data could influence the agent's behavior.
  • Ingestion points: Data returned by observe query, observe dataset view, observe skill view, and observe docs search commands.
  • Capability inventory: The skill has the ability to execute shell commands via the observe CLI.
  • Boundary markers: No delimiters or boundary instructions are provided to help the agent distinguish between data and instructions.
  • Sanitization: There is no evidence of sanitization or validation of the content pulled from the platform.
  • [COMMAND_EXECUTION]: The skill relies on executing shell commands through the observe CLI to perform its tasks. It specifically includes a mandatory instruction for the agent to run observe skill view observe-cli --content to dynamically fetch and load its own instruction set from the platform, which is a form of runtime instruction modification.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 18, 2026, 09:22 PM
Security Audit — agent-trust-hub — observe-cli