research
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to investigate external primary sources, including documentation and source code. This process ingests untrusted data into the agent's context without explicit boundary markers or sanitization instructions, creating a vulnerability to adversarial content embedded in those sources.
- Ingestion points: Official documentation, source code repositories, and first-party APIs.
- Boundary markers: None specified in the instructions.
- Capability inventory: Writing Markdown files to the local repository.
- Sanitization: No sanitization or validation of the researched content is mentioned.
- [COMMAND_EXECUTION]: The skill utilizes the
herdr pane splitcommand to manage background processes and environment variables. While this appears to be the primary intended functionality of the skill for delegating tasks, it involves the execution of shell commands and the management of sub-processes.
Audit Metadata