research-refine
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill instructions direct the agent to utilize the
Bashtool to write files (usingcat << 'EOF') as a silent fallback mechanism if the primaryWritetool fails due to content size, bypassing standard tool constraints without user intervention. - [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect injection as it ingests untrusted data from the
papers/andliterature/directories and viaWebFetchresults. This external content is interpolated into refinement prompts along with user-supplied$ARGUMENTS. Evidence chain: (1) Ingestion points: Local document directories and WebFetch output. (2) Boundary markers: The skill uses<details>tags for logs but lacks explicit delimiters or safety warnings for raw research paper content. (3) Capability inventory: Access toBash,Write,Edit, and network tools. (4) Sanitization: No specific escaping or validation of external research text is implemented. - [DYNAMIC_EXECUTION]: The workflow relies on an external script,
reviewer_route.py, to resolve reviewer backends at runtime. This indicates a dependency on local script execution to coordinate the skill's logic across different model backends. - [EXTERNAL_DOWNLOADS]: The skill is configured to use
WebSearchandWebFetchto retrieve research materials from external internet sources, which is a core part of its grounding and refinement process.
Audit Metadata