independent-research
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill encourages the agent to perform system reconnaissance by running commands such as
uname -a,which,node --version, andgit log. It also explicitly instructs the agent to "Test commands" and "Try it yourself first" when encountering potential solutions during research. - [INDIRECT_PROMPT_INJECTION]: The skill establishes a high-risk surface for indirect prompt injection by requiring the agent to ingest and act upon data from untrusted external sources.
- Ingestion points: External data is ingested via
WebSearch,WebFetch, and by reading GitHub issues and documentation pages (SKILL.md). - Boundary markers: The instructions lack any requirement for boundary markers or warnings to the agent to disregard instructions embedded within the fetched external data.
- Capability inventory: The agent has access to shell execution (
bash) and the ability to spawn subagents, which are used to "validate" and "test" research findings. - Sanitization: There is no mention of sanitizing, filtering, or sandboxing the commands or code snippets retrieved from the web before they are executed.
Audit Metadata