fast-track-ai-research
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to retrieve and process content from external web sources to create research artifacts.
- Ingestion points: External websites and primary sources retrieved during the research process (SKILL.md, Instruction 2).
- Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions when the agent processes retrieved external content, which could allow malicious instructions embedded in web pages to influence the agent.
- Capability inventory: The skill has the capability to write files to the file system (SKILL.md, Instruction 5) and execute a shell script (SKILL.md, Instruction 6).
- Sanitization: There are no instructions for sanitizing or validating the retrieved external content before it is processed or used in writing the research report.
- [COMMAND_EXECUTION]: Instruction 6 requires the agent to run a shell script at
../fast-track-ai-init/scripts/fast-track-ai-index.sh. This script is a local component used to validate and update the research index. While this is a functional part of the tool suite, it represents a command execution capability that is triggered after processing external research data.
Audit Metadata