gemini-cli-docs
Pass
Audited by Gen Agent Trust Hub on Mar 28, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill downloads documentation resources from the well-known domain
geminicli.com. This activity is central to the skill's purpose of maintaining a local repository of official help documents. - [COMMAND_EXECUTION]: Several management scripts use
subprocessto run Python andpipfor setting up dependencies and coordinating internal tasks. These operations are restricted to the skill's own environment and standard package management. - [PROMPT_INJECTION]: The skill processes external data from the web (documentation from
geminicli.com) and presents it to the agent. While this data is the intended subject of the skill, it represents a potential surface for indirect prompt injection if the source were compromised. The risk is negligible given the use of official domains and the skill's focus on technical content.
Audit Metadata