research
Pass
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
geminiCLI tool via bash commands to facilitate information gathering and processing. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its core function of processing untrusted external data.
- Ingestion points: Data is retrieved from the internet via the
WebSearchtool and from GitHub repositories via thedocs-seekerskill. - Boundary markers: There are no explicit delimiters or instructions provided to the agent to isolate external data from its primary instructions, increasing the risk of the agent following instructions embedded in research materials.
- Capability inventory: The agent has the ability to execute bash commands, use specialized search tools, and write reports to the local filesystem.
- Sanitization: No sanitization or validation of the external content is performed before it is integrated into the agent's context and analysis process.
Audit Metadata