research
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill involves ingesting untrusted data from external sources and project files, creating a potential surface for indirect prompt injection.
- Ingestion points: The skill instructions in SKILL.md direct the agent to perform web searches and read repository documentation such as AGENTS.md or other human-written docs.
- Boundary markers: The skill does not specify the use of boundary markers or delimiters when processing external search results or file content.
- Capability inventory: The skill includes file system write access to create research notes in the .agentflow/ directory and web search capabilities.
- Sanitization: There is no evidence of sanitization or validation routines for data retrieved from web searches or repository files before it is processed or stored.
Audit Metadata