search-and-fork
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external Gitee repositories, which creates a potential attack surface for indirect prompt injection.
- Ingestion points: In Step 5.2 (SKILL.md), the
get_file_contenttool is utilized to fetch the contents ofREADME.mdand other files from repositories identified during the search process. - Boundary markers: The instructions do not define clear boundary markers or provide explicit directives for the agent to ignore instructions embedded within the external file content.
- Capability inventory: The skill possesses capabilities including
search_open_source_repositories,get_file_content, andfork_repository. Malicious instructions in a repository's documentation could attempt to influence the agent's evaluation or subsequent actions. - Sanitization: No sanitization or filtering of the fetched repository content is specified before the data is presented to the model for analysis.
Audit Metadata