wiki-enrich
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local Python scripts (
research_wiki.py) and standard system utilities likecurl,grep, andgit. These are used for managing the wiki state and fetching data from official academic repositories. - [EXTERNAL_DOWNLOADS]: Fetches research paper abstracts and overviews from well-known and reputable services including
alphaxiv.organdarxiv.org. These operations are consistent with the skill's stated purpose of enriching a research wiki. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from external sources (arXiv and alphaXiv) to generate summaries. This creates a surface for indirect prompt injection if an attacker-controlled paper contains malicious instructions designed to influence the agent's behavior during the enrichment process.
- Ingestion points:
WebFetchfromalphaxiv.org,curlfromexport.arxiv.org, and reading local markdown files. - Boundary markers: None explicitly defined to separate untrusted source text from the agent's internal summarization instructions.
- Capability inventory: Uses
EditandWritetools to modify local filesystem content andBashfor utility operations. - Sanitization: No specific sanitization or filtering of the fetched content for prompt injection markers is documented.
Audit Metadata